© 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. 2-RES-JB
    11. 9497
    Prev
    Next
    INDEX
    Explanations

    words indicating priority or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "foremost" and its variations, indicating importance or precedence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chrom
    -0.85
     skelet
    -0.78
    aster
    -0.71
    ym
    -0.69
    employment
    -0.67
    thur
    -0.66
    isations
    -0.66
    appro
    -0.66
    zie
    -0.65
    ques
    -0.65
    POSITIVE LOGITS
     foremost
    1.17
     among
    0.81
    entimes
    0.80
     amongst
    0.80
    SourceFile
    0.76
    algia
    0.72
     priority
    0.68
     recognized
    0.67
    ashtra
    0.67
     sticking
    0.66
    Activations Density 0.008%

    No Known Activations