© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 11324
    Prev
    Next
    INDEX
    Explanations

    expressions related to miniature or small-scale items

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to miniature or small-scale concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tightly
    -0.83
     disproportionately
    -0.78
     thoroughly
    -0.75
     hardened
    -0.75
     ranks
    -0.74
     outnumbered
    -0.74
     commonly
    -0.74
     heavily
    -0.74
     mildly
    -0.74
     terminating
    -0.73
    POSITIVE LOGITS
    series
    1.42
    review
    1.31
    batch
    1.31
    dial
    1.30
    government
    1.29
    analysis
    1.28
    trans
    1.28
    deal
    1.28
    budget
    1.26
    crit
    1.26
    Activations Density 0.046%

    No Known Activations