© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35126
    Prev
    Next
    INDEX
    Explanations

    security-related terms and computer vulnerabilities like denial of service attacks

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    739
    +0.07
    0.7%
    150
    +0.05
    0.5%
    481
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.07
    0.28
    195
    +0.05
    0.01
    651
    +0.05
    0.13
    Negative Logits
    opa
    -0.41
    iatus
    -0.36
    sonian
    -0.36
    Cu
    -0.35
    gdala
    -0.35
    omez
    -0.35
    olor
    -0.34
    ross
    -0.34
    isu
    -0.34
    esta
    -0.34
    POSITIVE LOGITS
    finding
    0.43
     propagation
    0.38
     inference
    0.38
     assurance
    0.37
     tolerant
    0.37
     Enforcement
    0.36
     mitigation
    0.36
     suppression
    0.35
     markings
    0.35
     hazard
    0.35
    Activations Density 9.889%

    No Known Activations