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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 16886
    Prev
    Next
    INDEX
    Explanations

    statements related to discussion or analysis of specific topics

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with a period

    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
    icut
    -0.71
     extinguished
    -0.69
     crews
    -0.69
     aborted
    -0.68
    ãĤ´ãĥ³
    -0.68
     rid
    -0.68
     wreck
    -0.66
     worsh
    -0.65
    emic
    -0.65
     unlucky
    -0.65
    POSITIVE LOGITS
     Topics
    1.55
     Lastly
    1.24
     Specifically
    1.22
     Finally
    1.21
     Ultimately
    1.19
     Additionally
    1.15
     Readers
    1.12
     Drawing
    1.10
     Written
    1.08
     Also
    1.07
    Activations Density 0.312%

    No Known Activations