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. 2-RES-JB
    6. 16998
    Prev
    Next
    INDEX
    Explanations

    references to entities or items with the word "Red" in them

    oai_token-act-pair · gpt-3.5-turbo

    mentions 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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.88
    ILA
    -0.81
     4090
    -0.76
    ISTORY
    -0.74
    OHN
    -0.74
    gerald
    -0.72
     POLIT
    -0.70
    ammad
    -0.70
    ATURES
    -0.70
    Õ
    -0.70
    POSITIVE LOGITS
    uces
    1.07
     Sox
    1.06
    ucer
    0.99
    ucing
    0.99
    cliffe
    0.96
    neck
    0.96
    eem
    0.95
    rawn
    0.94
    emption
    0.93
    oubt
    0.92
    Activations Density 0.017%

    No Known Activations