© 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. 8-RES-JB
    11. 18507
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "Did you" prompting for engagement or response

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements directed towards the audience or reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Connector
    -0.76
    artifacts
    -0.76
    heter
    -0.73
    assemb
    -0.72
    limits
    -0.69
     presently
    -0.68
    yond
    -0.67
    Rel
    -0.66
    currently
    -0.63
    Dialogue
    -0.62
    POSITIVE LOGITS
     catch
    0.86
     typo
    0.86
     originally
    0.85
     earlier
    0.83
     stumble
    0.82
     mistake
    0.82
     previously
    0.81
     mention
    0.79
     miss
    0.78
     last
    0.75
    Activations Density 0.183%

    No Known Activations