© 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. 6-RES-JB
    11. 18467
    Prev
    Next
    INDEX
    Explanations

    specific mentions of a "portion" of something within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to segments or parts of a whole

    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
    generic
    -0.77
    Trend
    -0.71
    verbs
    -0.68
    ATHER
    -0.67
     Fighters
    -0.65
    NM
    -0.63
    raid
    -0.62
    urat
    -0.62
     darling
    -0.61
     opio
    -0.60
    POSITIVE LOGITS
     thereof
    1.08
    ials
    0.80
     of
    0.75
     ILCS
    0.75
    icularly
    0.71
    aler
    0.70
    OTUS
    0.70
     guiActiveUn
    0.69
    meal
    0.68
    edly
    0.67
    Activations Density 0.023%

    No Known Activations