© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7158
    Prev
    Next
    INDEX
    Explanations

    phrases related to requesting or asking for something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to requests or appeals for contributions or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aqu
    -0.66
    mk
    -0.64
     Trin
    -0.63
     Dock
    -0.63
    void
    -0.63
     RN
    -0.63
     Nanto
    -0.63
    than
    -0.62
     Laden
    -0.62
     Ange
    -0.62
    POSITIVE LOGITS
     solicit
    1.41
     solic
    1.28
     solicitation
    1.19
    olicited
    0.96
    yip
    0.88
     invitations
    0.82
     bids
    0.81
    umbnails
    0.80
    itta
    0.77
    ÃĥÃĤ
    0.76
    Activations Density 0.017%

    No Known Activations