© 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. 11-RES-JB
    11. 20689
    Prev
    Next
    INDEX
    Explanations

    phrases related to importance, significance, or impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significance or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    renheit
    -0.77
    amm
    -0.76
    rn
    -0.76
    urate
    -0.76
    erved
    -0.73
    ACK
    -0.72
    ldom
    -0.72
    alian
    -0.72
    late
    -0.72
    ©¶æ¥µ
    -0.71
    POSITIVE LOGITS
     drawback
    1.48
     problem
    1.44
     obstacle
    1.44
     question
    1.41
     takeaway
    1.40
     hurdle
    1.40
     difference
    1.38
     reason
    1.34
     flaw
    1.34
     downside
    1.31
    Activations Density 0.117%

    No Known Activations