© 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. 0-RES-JB
    11. 6820
    Prev
    Next
    INDEX
    Explanations

    words related to alcohol or substance use issues

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional expressions of sorrow and words related to luck or chance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lawn
    -0.86
    proxy
    -0.73
    aghan
    -0.72
     Clause
    -0.72
    icides
    -0.72
     [+]
    -0.72
    Hunt
    -0.71
    aceous
    -0.71
    thren
    -0.70
     Bohem
    -0.70
    POSITIVE LOGITS
     Pens
    1.99
     sob
    1.89
     Luck
    1.78
     Superintendent
    1.46
     superintendent
    1.34
     Sob
    1.22
    Luck
    1.18
     Baldwin
    1.17
     Rud
    1.15
    chenko
    1.03
    Activations Density 0.051%

    No Known Activations