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

    Neuronpedia

    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. 13559
    Prev
    Next
    INDEX
    Explanations

    names of months

    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
    371
    +0.04
    0.5%
    202
    +0.03
    0.4%
    252
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.04
    0.01
    657
    +0.03
    0.02
    86
    +0.03
    0.01
    Negative Logits
    croft
    -0.30
    edy
    -0.23
    Afee
    -0.22
    evin
    -0.22
    keley
    -0.22
    eve
    -0.21
    eless
    -0.21
    Sync
    -0.20
    bind
    -0.20
    rane
    -0.20
    POSITIVE LOGITS
    anguage
    0.27
    ãĥķãĤ©
    0.26
     mathemat
    0.26
    ÙĴ
    0.23
     fins
    0.23
     territ
    0.22
     olive
    0.22
     merch
    0.21
     nutrit
    0.21
     striped
    0.21
    Activations Density 0.063%

    No Known Activations