Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 674
    Prev
    Next
    INDEX
    Explanations

    words related to object disposal or release in a technical context

    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
    195
    +0.23
    0.7%
    578
    +0.17
    0.5%
    211
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.23
    0.04
    0
    +0.17
    0.04
    238
    +0.16
    0.04
    Negative Logits
    glers
    -1.35
    hetti
    -1.08
    erous
    -1.01
    ICAN
    -0.99
    asus
    -0.97
     Kinnikuman
    -0.95
     Juliet
    -0.94
    eers
    -0.90
    OHN
    -0.90
    urally
    -0.88
    POSITIVE LOGITS
    cipl
    1.64
    ciples
    1.48
    cerning
    1.44
    claimer
    1.44
    qus
    1.43
    enfranch
    1.43
    ruption
    1.41
    ribute
    1.40
    placed
    1.39
    ributed
    1.33
    Activations Density 0.618%

    No Known Activations