© 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. 23950
    Prev
    Next
    INDEX
    Explanations

    places or organizations providing specific services or resources

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of centers

    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
    ãĥīãĥ©
    -0.70
    wcsstore
    -0.68
     Bagg
    -0.67
    THER
    -0.65
    proof
    -0.64
    TON
    -0.64
    BIT
    -0.63
     Lords
    -0.63
     Hazard
    -0.63
    gee
    -0.63
    POSITIVE LOGITS
     centers
    1.12
    pieces
    0.92
    chool
    0.89
     centres
    0.88
     certific
    0.85
    bard
    0.82
    pace
    0.81
    hips
    0.79
    ensical
    0.77
    rals
    0.75
    Activations Density 0.009%

    No Known Activations