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. 9-RES-JB
    6. 11115
    Prev
    Next
    INDEX
    Explanations

    instances where a hypothetical situation is being discussed or imagined

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements using the phrase "if it were."

    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
     è£ıç
    -0.66
    oria
    -0.62
    abre
    -0.61
    NOTE
    -0.59
    span
    -0.59
    è¦ļéĨĴ
    -0.57
     fascination
    -0.57
     emphasis
    -0.56
    Ê
    -0.56
     tremend
    -0.55
    POSITIVE LOGITS
     hypot
    0.83
    webkit
    0.79
    wolves
    0.78
    nt
    0.76
     somehow
    0.67
    omorphic
    0.65
     truly
    0.63
    agall
    0.62
     tomorrow
    0.62
     genuinely
    0.62
    Activations Density 0.110%

    No Known Activations