© 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. 6472
    Prev
    Next
    INDEX
    Explanations

    words related to spatial or opposing relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to different sides or perspectives in a debate or conflict

    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
    endi
    -0.84
    ESCO
    -0.80
    yrinth
    -0.76
    erion
    -0.73
    untu
    -0.72
    itative
    -0.71
    Ĥİ
    -0.68
    yssey
    -0.65
    acan
    -0.64
    ogy
    -0.64
    POSITIVE LOGITS
    kick
    1.06
     thereof
    0.89
    board
    0.81
    burn
    0.80
    side
    0.77
    boards
    0.77
     of
    0.76
    bars
    0.71
     Za
    0.70
    real
    0.68
    Activations Density 0.034%

    No Known Activations