© 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. 9-RES-JB
    11. 22735
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to key points or important aspects

    oai_token-act-pair · gpt-3.5-turbo

    key points or themes emphasized in a discussion or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etimes
    -0.79
    each
    -0.76
    renheit
    -0.72
    ruary
    -0.72
    UME
    -0.69
    rosso
    -0.68
    ipel
    -0.68
    ORTS
    -0.68
    FIL
    -0.68
    late
    -0.68
    POSITIVE LOGITS
     reason
    1.43
     drawback
    1.37
     implication
    1.36
     takeaway
    1.35
     caveat
    1.34
     difference
    1.34
     downside
    1.30
     concern
    1.29
     question
    1.28
     problem
    1.27
    Activations Density 0.117%

    No Known Activations