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. 8-RES-JB
    6. 9365
    Prev
    Next
    INDEX
    Explanations

    names or phrases related to a person or entity named "Rev."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Rev," indicating a focus on something related to revival, reviews, or individuals associated with revival movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holders
    -0.74
    女
    -0.66
    matical
    -0.65
     TOTAL
    -0.61
    boxes
    -0.61
    berman
    -0.61
     charism
    -0.60
    MENTS
    -0.59
    bags
    -0.57
     NIC
    -0.57
    POSITIVE LOGITS
    isions
    1.22
    olved
    1.22
    ivals
    1.19
    olutions
    1.17
    olve
    1.11
    olver
    1.11
    ascular
    1.10
    amping
    1.09
    ulsion
    1.08
    olving
    1.06
    Activations Density 0.029%

    No Known Activations