© 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. 3327
    Prev
    Next
    INDEX
    Explanations

    the verb "carve" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "carve" and its variations

    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
    enez
    -0.71
    abol
    -0.67
     Bern
    -0.64
    REL
    -0.64
    COMPLE
    -0.64
     Michelle
    -0.63
    MAT
    -0.63
     Glob
    -0.63
     Bru
    -0.61
     Dem
    -0.61
    POSITIVE LOGITS
     carving
    1.36
     carve
    1.33
     carved
    1.23
    smanship
    0.89
     chops
    0.88
     corrid
    0.87
    cuts
    0.86
     sculptures
    0.85
    fters
    0.79
    ciating
    0.78
    Activations Density 0.007%

    No Known Activations