© 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. 1-RES-JB
    11. 6392
    Prev
    Next
    INDEX
    Explanations

    the word "ane"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals with the name "Cane" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irements
    -0.78
    ntil
    -0.77
    é¾įå¥ij士
    -0.72
    è¦ļéĨĴ
    -0.72
    aeper
    -0.70
     Aval
    -0.66
    lished
    -0.66
    ODUCT
    -0.63
    ealous
    -0.63
    spring
    -0.60
    POSITIVE LOGITS
    ane
    1.30
    leigh
    0.86
    cia
    0.84
    ucl
    0.82
    ffe
    0.80
    ity
    0.76
    gan
    0.76
    ji
    0.76
    gas
    0.74
    jad
    0.74
    Activations Density 0.007%

    No Known Activations