© 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. 0-RES-JB
    11. 1287
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant change or improvement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transformation and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liam
    -0.87
     surveyed
    -0.75
    pots
    -0.74
    gyn
    -0.73
     mourn
    -0.72
     engaged
    -0.71
     behaved
    -0.71
    oresc
    -0.70
     briefed
    -0.69
     teamed
    -0.68
    POSITIVE LOGITS
     transformation
    1.90
     elimination
    1.83
     manipulation
    1.73
     modification
    1.72
     deletion
    1.72
     abandonment
    1.70
     rejection
    1.68
     insertion
    1.67
     reversal
    1.63
     realization
    1.63
    Activations Density 0.114%

    No Known Activations