© 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. 9377
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing commitment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "commitment"

    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
    adish
    -0.73
    dos
    -0.67
    avis
    -0.65
     Caucas
    -0.65
    phe
    -0.65
    isen
    -0.64
    bin
    -0.64
    rors
    -0.62
    walking
    -0.61
    ox
    -0.61
    POSITIVE LOGITS
     commitment
    1.14
     commitments
    0.94
     Commit
    0.86
     allegiance
    0.83
    irmation
    0.82
    ilitary
    0.76
     pledge
    0.74
    gence
    0.74
    commit
    0.73
    xual
    0.71
    Activations Density 0.014%

    No Known Activations