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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5369
    Prev
    Next
    INDEX
    Explanations

    commands or instructions related to computer programming and technical setups, specifically emphasizing aspects related to control

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.21
    0.7%
    59
    +0.18
    0.6%
    218
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.21
    0.05
    288
    +0.18
    0.05
    271
    +0.16
    0.04
    Negative Logits
    istle
    -1.04
     Honour
    -0.94
    olit
    -0.91
    Na
    -0.89
    ich
    -0.89
    à¤
    -0.88
    elt
    -0.88
    tein
    -0.88
    iscopal
    -0.88
    ead
    -0.87
    POSITIVE LOGITS
     freak
    1.19
    eering
    1.12
    rador
    1.08
     fre
    1.07
    eer
    1.06
     levers
    1.06
    eers
    1.05
     steering
    1.04
    vier
    1.04
     valves
    1.00
    Activations Density 0.567%

    No Known Activations