© 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. 7105
    Prev
    Next
    INDEX
    Explanations

    numerical information or quantities given in relation to a certain context or condition

    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
    quit
    -0.73
    ãĤº
    -0.64
    anwhile
    -0.61
    ãĤ¿
    -0.60
    icides
    -0.59
    gencies
    -0.58
    window
    -0.58
    âĵĺ
    -0.57
     happiest
    -0.56
    tions
    -0.55
    POSITIVE LOGITS
     partially
    1.07
     partly
    0.96
     SOME
    0.86
     partial
    0.84
     temporarily
    0.83
     half
    0.79
     one
    0.77
     some
    0.77
     twice
    0.75
     tacit
    0.73
    Activations Density 0.043%

    No Known Activations