© 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. 6-RES-JB
    11. 17477
    Prev
    Next
    INDEX
    Explanations

    mentions directed towards or involving users or customers

    oai_token-act-pair · gpt-3.5-turbo

    references to people engaging with content or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REDACTED
    -0.76
    votes
    -0.59
    WOR
    -0.56
     Thing
    -0.54
    kun
    -0.54
     Scar
    -0.53
     Ratt
    -0.53
    ASED
    -0.53
    Tang
    -0.52
    ITED
    -0.51
    POSITIVE LOGITS
     downstream
    0.74
    hip
    0.73
    ividually
    0.70
     beware
    0.67
    folk
    0.64
    hips
    0.63
     visualize
    0.62
    iners
    0.62
    inarily
    0.62
    inki
    0.61
    Activations Density 0.208%

    No Known Activations