© 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. 8-RES-JB
    11. 7807
    Prev
    Next
    INDEX
    Explanations

    numeric information presented in a specific format, potentially indicating statistics or data points

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" accompanied by various contexts or specific locations

    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
    Aid
    -0.69
    WER
    -0.65
    tackle
    -0.65
    meet
    -0.61
    Material
    -0.61
    THIS
    -0.61
    UID
    -0.61
    Available
    -0.59
    mediated
    -0.59
    Written
    -0.58
    POSITIVE LOGITS
     subsequent
    0.71
     others
    0.68
     hers
    0.68
     theirs
    0.67
     Cind
    0.67
     thereafter
    0.64
    iations
    0.63
     Coff
    0.62
     ours
    0.61
     another
    0.61
    Activations Density 0.242%

    No Known Activations