© 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. 12160
    Prev
    Next
    INDEX
    Explanations

    dates and events involving a person named "He"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, likely a prominent figure

    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
     guiActiveUnfocused
    -0.72
    duc
    -0.65
    CAP
    -0.64
    earch
    -0.62
    Untitled
    -0.58
    agogue
    -0.58
    ãĥ¬
    -0.57
    âĻ¦
    -0.56
    DAY
    -0.55
    outer
    -0.54
    POSITIVE LOGITS
    'll
    1.11
    resy
    1.08
    'd
    0.99
    pherd
    0.89
    ppard
    0.87
    zbollah
    0.87
    've
    0.84
    miah
    0.83
     therefore
    0.81
    reditary
    0.80
    Activations Density 0.199%

    No Known Activations