© 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. 2-RES-JB
    11. 23860
    Prev
    Next
    INDEX
    Explanations

    phrases related to requesting, asking for, or seeking something

    oai_token-act-pair · gpt-3.5-turbo

    instances of solicitation-related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    than
    -0.76
    century
    -0.69
    void
    -0.68
    fall
    -0.67
    Ast
    -0.65
    Known
    -0.65
    Dad
    -0.65
     Trin
    -0.64
     Blessed
    -0.64
    Credits
    -0.64
    POSITIVE LOGITS
     solic
    1.45
     solicitation
    1.29
     solicit
    1.26
    olicited
    0.93
    ÃĥÃĤ
    0.85
    umbnails
    0.85
     bids
    0.80
     volunte
    0.80
     fundra
    0.79
    cffff
    0.78
    Activations Density 0.007%

    No Known Activations