© 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. 9-RES-JB
    11. 1003
    Prev
    Next
    INDEX
    Explanations

    adjectives relating to color, specifically the color red

    oai_token-act-pair · gpt-3.5-turbo

    references to the color red

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ernel
    -0.81
    agall
    -0.74
    awaru
    -0.72
    Ö¼
    -0.70
    Reloaded
    -0.68
    vre
    -0.68
    UGH
    -0.67
    XT
    -0.67
     Lank
    -0.65
    ILA
    -0.65
    POSITIVE LOGITS
    efined
    1.23
    iscovered
    1.14
    irection
    1.13
    neck
    1.13
    oubt
    1.12
    iscover
    1.12
    iscovery
    1.11
    rawn
    1.08
    oub
    1.04
     velvet
    1.00
    Activations Density 0.026%

    No Known Activations