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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23611
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences expressing uncertainty or a contrasting viewpoint

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express uncertainty or conditionality regarding situations or outcomes

    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
    ãĥ³ãĤ¸
    -0.74
     Ez
    -0.59
    enegger
    -0.58
    Ô
    -0.58
    annels
    -0.57
    sbm
    -0.57
    Billy
    -0.56
     Byrd
    -0.56
    Ts
    -0.55
     1928
    -0.54
    POSITIVE LOGITS
    uthor
    0.74
    lisher
    0.71
     recons
    0.69
     intervened
    0.65
    assador
    0.64
     Geek
    0.63
     succeeds
    0.62
    ucer
    0.61
     proves
    0.61
     ado
    0.60
    Activations Density 0.184%

    No Known Activations