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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7599
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to computer programming and code syntax

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas and parentheses

    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
     behavi
    -0.66
     vulner
    -0.65
     thous
    -0.64
     explan
    -0.60
    account
    -0.58
    amorph
    -0.57
     exha
    -0.57
     horizont
    -0.57
     disadvant
    -0.56
     advis
    -0.56
    POSITIVE LOGITS
    mosp
    0.69
     Psy
    0.64
    nee
    0.63
     Squirrel
    0.60
    actionDate
    0.60
     ILCS
    0.56
    IGH
    0.53
     sidx
    0.53
    zbollah
    0.51
    ffic
    0.50
    Activations Density 0.113%

    No Known Activations