© 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. 2-RES-JB
    11. 17824
    Prev
    Next
    INDEX
    Explanations

    terms containing the string "kn" followed by a digit

    oai_token-act-pair · gpt-3.5-turbo

    words related to "knock."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DEM
    -0.92
    ahime
    -0.77
     Gum
    -0.73
    REDACTED
    -0.72
    sem
    -0.72
    IUM
    -0.71
    ORGE
    -0.70
    urdue
    -0.69
     Uran
    -0.68
     Wikimedia
    -0.67
    POSITIVE LOGITS
    uckle
    1.12
    ivable
    1.04
    ocking
    1.03
    uckles
    1.00
    kn
    0.98
     Kn
    0.94
    ows
    0.93
    itting
    0.93
    ock
    0.93
    icker
    0.91
    Activations Density 0.010%

    No Known Activations