© 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. 1-RES-JB
    11. 20222
    Prev
    Next
    INDEX
    Explanations

    references to political or social initiatives

    oai_token-act-pair · gpt-3.5-turbo

    mentions of initiatives or proposals aimed at achieving specific goals or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oil
    -0.86
    oiler
    -0.83
    bane
    -0.72
    onyms
    -0.70
    parts
    -0.69
    ummies
    -0.69
    olia
    -0.68
    mbuds
    -0.67
    gone
    -0.65
    fell
    -0.64
    POSITIVE LOGITS
     initiative
    1.19
    eers
    0.99
    ually
    0.85
    gomery
    0.78
     initiatives
    0.75
    ĸļ
    0.73
    naire
    0.72
     effort
    0.71
     Initiative
    0.69
    ilus
    0.67
    Activations Density 0.008%

    No Known Activations