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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12193
    Prev
    Next
    INDEX
    Explanations

    locations described as being underground or buried

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and phrases related to locations or placements

    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
    usterity
    -0.78
    utsche
    -0.74
    entity
    -0.71
    oyal
    -0.70
    thood
    -0.69
    gey
    -0.67
    zinski
    -0.65
    andum
    -0.65
    gression
    -0.64
    ict
    -0.64
    POSITIVE LOGITS
     where
    1.50
    where
    1.25
     whence
    1.24
     overlooking
    1.15
     surrounded
    1.11
     flanked
    1.03
     wherein
    1.01
     located
    0.95
     unnoticed
    0.95
     awaiting
    0.94
    Activations Density 0.379%

    No Known Activations