© 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. 11-RES-JB
    11. 7163
    Prev
    Next
    INDEX
    Explanations

    legal and administrative terms

    oai_token-act-pair · gpt-3.5-turbo
    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
    beard
    -0.84
    ILY
    -0.73
     buckle
    -0.65
     Nieto
    -0.61
     Belt
    -0.61
     lightly
    -0.61
    landish
    -0.60
     err
    -0.59
    theless
    -0.59
     mist
    -0.59
    POSITIVE LOGITS
    ations
    2.34
    ators
    2.31
    atory
    2.20
    ator
    2.08
    ational
    1.95
    ative
    1.88
    atio
    1.86
    atories
    1.84
    ating
    1.80
    ates
    1.74
    Activations Density 0.098%

    No Known Activations