© 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. 10-RES-JB
    11. 7365
    Prev
    Next
    INDEX
    Explanations

    statements related to beliefs or commitments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to commitment and advocacy for social issues

    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
    ?).
    -0.84
    NetMessage
    -0.75
    maybe
    -0.70
    pload
    -0.70
     suddenly
    -0.69
    soDeliveryDate
    -0.68
    ptoms
    -0.68
    unknown
    -0.68
    ?)
    -0.67
    ifix
    -0.67
    POSITIVE LOGITS
     inclusive
    1.18
     excellence
    1.18
     diversity
    1.16
    cellence
    1.15
     integrity
    1.14
     respectful
    1.12
     transparency
    1.10
    clus
    1.10
     openness
    1.10
     professionalism
    1.08
    Activations Density 0.491%

    No Known Activations