© 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. 10135
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations, laws, and controls

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation in various forms, particularly periods

    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
    wcs
    -0.72
    liner
    -0.66
    nen
    -0.63
    onite
    -0.63
    stadt
    -0.59
    abies
    -0.59
    ozy
    -0.57
    cil
    -0.56
     favour
    -0.56
    iera
    -0.55
    POSITIVE LOGITS
     .
    1.68
     ."
    1.67
     .)
    1.40
     ..
    1.07
     ._
    1.07
    _.
    1.04
     ,"
    0.99
    -.
    0.98
     (.
    0.82
    `.
    0.81
    Activations Density 0.018%

    No Known Activations