© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 376
    Prev
    Next
    INDEX
    Explanations

    words related to firearms and ammunition

    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
    373
    +0.08
    0.5%
    109
    +0.07
    0.4%
    92
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.08
    -0.01
    406
    +0.07
    0.03
    232
    +0.07
    0.03
    Negative Logits
     Valkyrie
    -0.55
    CHR
    -0.48
     aerial
    -0.48
    Beginning
    -0.47
    USD
    -0.47
    sterdam
    -0.45
     Divinity
    -0.44
    £ı
    -0.44
    ISSION
    -0.44
    SPONSORED
    -0.44
    POSITIVE LOGITS
    oming
    0.57
    bery
    0.56
    agg
    0.55
    ba
    0.54
    gging
    0.54
    urn
    0.52
    ules
    0.52
    ody
    0.52
    oss
    0.52
    ug
    0.51
    Activations Density 0.095%

    No Known Activations