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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 17081
    Prev
    Next
    INDEX
    Explanations

    punctuation characters and markers indicating text division

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to comparison or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    culosis
    -0.55
    anwhile
    -0.53
    emale
    -0.50
    代
    -0.49
     Royale
    -0.47
    ugu
    -0.47
    vertis
    -0.45
    ãĥ¼ãĥĨ
    -0.45
    orst
    -0.44
     pione
    -0.44
    POSITIVE LOGITS
    pmwiki
    0.57
    NetMessage
    0.54
    natureconservancy
    0.50
    rower
    0.46
     Speedway
    0.45
    ¶
    0.45
     embodiments
    0.44
     disclaim
    0.44
     Flavoring
    0.43
     philosophers
    0.42
    Activations Density 2.272%

    No Known Activations