© 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. 3-RES-JB
    11. 22660
    Prev
    Next
    INDEX
    Explanations

    the phrase "first and foremost" in texts

    oai_token-act-pair · gpt-3.5-turbo

    terms that emphasize primary importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skelet
    -0.82
    chrom
    -0.81
    rise
    -0.66
    aster
    -0.66
    arter
    -0.63
    ideon
    -0.63
    ending
    -0.62
    inter
    -0.61
    olls
    -0.61
    hex
    -0.60
    POSITIVE LOGITS
     foremost
    1.10
     amongst
    0.82
     among
    0.82
    tenance
    0.76
     priority
    0.73
     delinquent
    0.72
    entimes
    0.72
    SourceFile
    0.71
     importance
    0.69
     Important
    0.67
    Activations Density 0.008%

    No Known Activations