© 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. 19379
    Prev
    Next
    INDEX
    Explanations

    computer code snippets or corrupted text, with some including words related to international politics and conflict

    oai_token-act-pair · gpt-3.5-turbo

    numerical sequences and codes

    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
    sembly
    -0.72
    Higher
    -0.68
     purpose
    -0.66
    acebook
    -0.66
     respectively
    -0.65
    $.
    -0.61
    eatures
    -0.61
     contrasting
    -0.59
     purposes
    -0.58
    Else
    -0.57
    POSITIVE LOGITS
    ²
    0.86
    ãģ®ç
    0.80
    ¶
    0.78
    ãģ®å
    0.76
    ±
    0.73
    Į
    0.72
    ¶æ
    0.71
    ãģ®æ
    0.71
    ãģ®é
    0.70
     Converted
    0.70
    Activations Density 0.263%

    No Known Activations