© 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. 8-RES-JB
    11. 2689
    Prev
    Next
    INDEX
    Explanations

    positive news or updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating positive outcomes or news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.74
    abwe
    -0.66
    renheit
    -0.65
    Cola
    -0.64
    uilding
    -0.64
    zai
    -0.62
    jri
    -0.61
    arate
    -0.61
    atever
    -0.61
     appropriated
    -0.60
    POSITIVE LOGITS
     thing
    0.85
    est
    0.84
    iest
    0.80
     folks
    0.78
     stuff
    0.78
     guy
    0.75
     bits
    0.74
     ol
    0.74
     ones
    0.73
     guys
    0.73
    Activations Density 0.084%

    No Known Activations