© 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. 6-RES-JB
    11. 19723
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    percentage figures and their associated context in economic or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scarce
    -0.64
    ãĥ¤
    -0.64
     neighb
    -0.62
    lict
    -0.62
     lone
    -0.57
     larg
    -0.57
    byter
    -0.57
    pressed
    -0.56
    pton
    -0.56
    IRT
    -0.55
    POSITIVE LOGITS
    xual
    0.83
    uary
    0.79
     Decay
    0.78
     increments
    0.77
     ABV
    0.76
    rowth
    0.72
    factor
    0.71
     apiece
    0.70
    +.
    0.70
    elsius
    0.70
    Activations Density 0.062%

    No Known Activations