Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9852
    Prev
    Next
    INDEX
    Explanations

    references to the color red

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "red."

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

    No Comments

    Negative Logits
    ILA
    -0.84
     Lank
    -0.80
    UGH
    -0.79
    ETHOD
    -0.78
    ernel
    -0.77
    Ö¼
    -0.76
    agall
    -0.76
    HAEL
    -0.74
    llah
    -0.72
    Technical
    -0.71
    POSITIVE LOGITS
    rawn
    1.17
    neck
    1.12
    oubt
    1.10
    efined
    1.08
    oub
    1.02
    headed
    1.01
     velvet
    0.99
    iscovered
    0.96
    iscovery
    0.93
    iscover
    0.91
    Activations Density 0.024%

    No Known Activations