© 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. 2680
    Prev
    Next
    INDEX
    Explanations

    words related to influencing or determining factors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of factors contributing to various outcomes or conditions

    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
    alach
    -0.85
    ©¶æ
    -0.79
    dos
    -0.78
    phis
    -0.77
    oÄŁ
    -0.77
    ichick
    -0.76
    escription
    -0.75
    guyen
    -0.74
    gem
    -0.74
    quartered
    -0.73
    POSITIVE LOGITS
     factors
    0.90
    factor
    0.86
     factor
    0.84
     influencing
    0.80
     contributing
    0.80
     affecting
    0.78
     Factors
    0.77
     equation
    0.72
    iator
    0.72
     predis
    0.71
    Activations Density 0.033%

    No Known Activations