© 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. 11669
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions, comments, and statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to communication or commentary

    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
    ratulations
    -0.83
    lection
    -0.68
    lock
    -0.66
    Gear
    -0.63
    yrinth
    -0.60
    geoning
    -0.58
     Passage
    -0.58
     Kens
    -0.57
     Syri
    -0.57
     Dot
    -0.56
    POSITIVE LOGITS
    ometimes
    1.03
     yearly
    1.00
     regularly
    0.88
     daily
    0.88
     nightly
    0.87
     weekly
    0.85
     annually
    0.82
    advertisement
    0.80
     routinely
    0.79
     annual
    0.79
    Activations Density 0.901%

    No Known Activations