© 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. 2-RES-JB
    11. 3886
    Prev
    Next
    INDEX
    Explanations

    references to the American Broadcasting Company (ABC)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the ABC media organization

    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
    irts
    -0.76
    boarding
    -0.70
    ances
    -0.69
    lights
    -0.67
    vik
    -0.67
    agues
    -0.66
    ainer
    -0.63
    faces
    -0.63
    antics
    -0.63
    olas
    -0.63
    POSITIVE LOGITS
    DEF
    1.25
     Mub
    0.90
     ABC
    0.89
    ABC
    0.80
    nect
    0.79
    IRO
    0.77
    NEWS
    0.77
    é¾
    0.75
    DF
    0.73
    NF
    0.70
    Activations Density 0.004%

    No Known Activations