© 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. 2-RES-JB
    11. 8413
    Prev
    Next
    INDEX
    Explanations

    mentions of research studies or polls being conducted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "conducted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esa
    -0.75
    Hom
    -0.72
    edia
    -0.65
    loaded
    -0.64
    dim
    -0.62
    mob
    -0.61
    urrection
    -0.60
    killing
    -0.60
    pine
    -0.56
     Chimera
    -0.56
    POSITIVE LOGITS
     conducted
    0.86
    onduct
    0.75
    atform
    0.74
    insula
    0.73
    arnaev
    0.73
    uations
    0.72
    Īè
    0.72
    в
    0.71
    æĸ¹
    0.69
    avorite
    0.68
    Activations Density 0.015%

    No Known Activations