© 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. 19937
    Prev
    Next
    INDEX
    Explanations

    words related to well-known individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or entities associated with political contexts

    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
     Ridley
    -0.71
    stone
    -0.67
    advertising
    -0.66
     Jessie
    -0.65
    NL
    -0.62
     Hungry
    -0.60
    CLASSIFIED
    -0.58
    anking
    -0.58
    stones
    -0.57
     Scream
    -0.57
    POSITIVE LOGITS
    oba
    4.79
    zeb
    1.30
    oshop
    1.05
    agara
    0.90
    opa
    0.88
    owa
    0.87
    hemat
    0.85
    ensis
    0.84
    icut
    0.84
    zona
    0.83
    Activations Density 0.018%

    No Known Activations