© 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. 19729
    Prev
    Next
    INDEX
    Explanations

    dates, events, and changes over time

    oai_token-act-pair · gpt-3.5-turbo

    events and timelines related to significant occurrences

    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
     continuum
    -0.58
    poor
    -0.56
     sexes
    -0.56
    ordinary
    -0.53
    oir
    -0.50
     Subtle
    -0.49
    Poor
    -0.49
     extremes
    -0.49
     degrade
    -0.48
    "}],"
    -0.48
    POSITIVE LOGITS
     Deadline
    0.55
     spokeswoman
    0.55
     scrapped
    0.49
     HuffPost
    0.49
     reinstated
    0.48
     shortly
    0.48
     announced
    0.48
     Orbital
    0.47
     Bezos
    0.47
     previously
    0.47
    Activations Density 1.235%

    No Known Activations