© 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. 8-RES-JB
    11. 2588
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sign, indication, or proof of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating signs or evidence of various conditions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tones
    -0.72
    onyms
    -0.72
    ancies
    -0.70
    ascus
    -0.67
    hari
    -0.66
     swaps
    -0.66
    quer
    -0.66
     Antiqu
    -0.65
    ulner
    -0.64
    asions
    -0.63
    POSITIVE LOGITS
    ariat
    0.72
    alled
    0.72
    ially
    0.72
     indication
    0.71
    ifier
    0.70
    Sign
    0.69
     indicative
    0.68
    rance
    0.67
     of
    0.67
    reader
    0.66
    Activations Density 0.088%

    No Known Activations