Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 250
    Prev
    Next
    INDEX
    Explanations

    instances where an alternative or different method or choice is being described or suggested

    oai_token-act-pair · gpt-3.5-turbo

    the word "instead" indicative of alternatives or substitutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andestine
    -0.63
    ESE
    -0.63
    Interstitial
    -0.61
    estern
    -0.60
    ental
    -0.57
    vez
    -0.56
    ankind
    -0.56
    ENTS
    -0.55
    nce
    -0.54
    IENT
    -0.52
    POSITIVE LOGITS
     thereof
    0.95
     of
    0.93
    of
    0.80
     opting
    0.76
    ilon
    0.74
    ta
    0.69
    fitted
    0.66
     preferring
    0.66
     OF
    0.63
    paces
    0.63
    Activations Density 0.025%

    No Known Activations