© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23687
    Prev
    Next
    INDEX
    Explanations

    the causes and contributing factors of certain events or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causation or factors contributing to various outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.73
    atri
    -0.72
    heit
    -0.72
    uci
    -0.70
    atomic
    -0.70
    ancies
    -0.68
    alach
    -0.63
    orks
    -0.61
     composure
    -0.61
    aram
    -0.60
    POSITIVE LOGITS
     determining
    0.81
     motivating
    0.78
     behind
    0.74
     driving
    0.73
     unlocking
    0.71
     why
    0.69
     thereof
    0.68
     contributing
    0.66
    ainer
    0.66
     fueling
    0.65
    Activations Density 0.114%

    No Known Activations