© 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. 0-RES-JB
    11. 23362
    Prev
    Next
    INDEX
    Explanations

    the word "Pen" followed by a single lowercase letter

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Pen" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overload
    -0.89
    ãģł
    -0.70
    mix
    -0.67
     eclectic
    -0.66
    Ö¼
    -0.61
     overloaded
    -0.61
     zip
    -0.60
    azz
    -0.60
    balanced
    -0.60
     hijacked
    -0.60
    POSITIVE LOGITS
     Pen
    4.07
    Pen
    3.00
     pen
    2.11
     Pens
    1.92
    pen
    1.88
     pens
    1.57
     Penalty
    1.19
     Pun
    1.19
     Penet
    1.18
     pencil
    1.16
    Activations Density 0.017%

    No Known Activations