© 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. 1-RES-JB
    11. 19661
    Prev
    Next
    INDEX
    Explanations

    keywords related to the word "aster"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "aster"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANY
    -0.73
    UME
    -0.70
    WI
    -0.69
    %]
    -0.64
    ENSE
    -0.61
     narrow
    -0.61
    UTERS
    -0.60
    bes
    -0.58
    IGH
    -0.58
    bis
    -0.56
    POSITIVE LOGITS
    aster
    1.22
    dayName
    0.85
    asting
    0.83
    ãĥ¼ãĥĨãĤ£
    0.80
    tainment
    0.78
    asters
    0.78
    astic
    0.77
    adeon
    0.76
    emort
    0.76
    lite
    0.76
    Activations Density 0.007%

    No Known Activations