© 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. 1076
    Prev
    Next
    INDEX
    Explanations

    references to specific financial news outlet sections

    oai_token-act-pair · gpt-3.5-turbo

    references to the website WSJ (Wall Street Journal)

    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
    ments
    -0.77
    orescent
    -0.70
    mented
    -0.69
    staking
    -0.68
    Ô
    -0.68
    mentation
    -0.67
    aneous
    -0.66
    itate
    -0.63
    ancy
    -0.63
    orate
    -0.62
    POSITIVE LOGITS
     WS
    0.95
    pace
    0.93
    WS
    0.92
    GF
    0.88
    ullivan
    0.84
    DF
    0.84
    nesday
    0.84
    erver
    0.80
    kins
    0.79
    aunders
    0.78
    Activations Density 0.007%

    No Known Activations