© 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. 2-RES-JB
    11. 669
    Prev
    Next
    INDEX
    Explanations

    acronyms or initialisms related to organizations

    oai_token-act-pair · gpt-4-turbo

    organizations or institutions with abbreviations or acronyms

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and abbreviations related to organizations or systems

    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
    away
    -0.77
    orses
    -0.75
    itably
    -0.71
    butt
    -0.68
    obin
    -0.67
    itable
    -0.67
    ceptive
    -0.66
    aways
    -0.66
    opol
    -0.65
    xiety
    -0.65
    POSITIVE LOGITS
     CPS
    1.04
    PS
    1.00
     reluct
    0.94
    INO
    0.92
    ULE
    0.89
    EVA
    0.88
    KY
    0.87
    ilon
    0.86
    LAB
    0.85
    CENT
    0.85
    Activations Density 0.017%

    No Known Activations