© 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. 4209
    Prev
    Next
    INDEX
    Explanations

    phrases related to "asm", likely an abbreviation for "sarcasm"

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of muscle spasms and associated conditions

    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
    ©¶æ
    -0.79
    tops
    -0.74
    llo
    -0.69
    PDATE
    -0.69
    VICE
    -0.66
    ttes
    -0.65
    VEN
    -0.65
    nda
    -0.61
    backs
    -0.61
    gg
    -0.61
    POSITIVE LOGITS
    iasm
    1.13
    ussen
    1.09
    atic
    0.93
    icity
    0.92
    orph
    0.92
    atural
    0.92
    channelAvailability
    0.91
    otics
    0.89
    olit
    0.89
    uture
    0.88
    Activations Density 0.053%

    No Known Activations