© 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. 6263
    Prev
    Next
    INDEX
    Explanations

    terms related to degradation or criticism

    oai_token-act-pair · gpt-3.5-turbo

    references to the Democratic Party or related political terms

    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
    wood
    -0.75
    VT
    -0.71
    ibles
    -0.68
    eat
    -0.68
    burning
    -0.67
    axter
    -0.67
    parts
    -0.66
    answered
    -0.66
    hyde
    -0.66
    onday
    -0.64
    POSITIVE LOGITS
     dem
    3.82
    dem
    1.91
     Dem
    1.85
    Dem
    1.58
     DEM
    1.46
    DEM
    1.33
     den
    1.26
     delim
    1.03
     cens
    0.99
     Dism
    0.92
    Activations Density 0.009%

    No Known Activations