© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 14017
    Prev
    Next
    INDEX
    Explanations

    mentions of the keyword "Fil" or variations like "fil" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific entity or name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.64
     compr
    -0.64
     Butterfly
    -0.61
     Stand
    -0.58
    eer
    -0.58
     Dakota
    -0.58
     Sovereign
    -0.57
     dummy
    -0.57
     convict
    -0.57
     Barnes
    -0.57
    POSITIVE LOGITS
    igree
    1.35
    ters
    1.28
    tered
    1.23
    tering
    1.15
    thy
    1.12
    ming
    1.09
    ms
    1.03
    ename
    0.99
    cipled
    0.99
    terness
    0.98
    Activations Density 0.034%

    No Known Activations