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. 6837
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Rash"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ash" and its variations in different contexts

    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
    theless
    -0.59
     glasses
    -0.58
     midterm
    -0.56
     thinner
    -0.56
    ebus
    -0.55
     fart
    -0.55
    etheless
    -0.55
     livest
    -0.54
    eering
    -0.54
     Duff
    -0.53
    POSITIVE LOGITS
    nikov
    0.98
    ti
    0.98
    tu
    0.93
    ares
    0.91
    mir
    0.91
    imi
    0.89
    tar
    0.87
    adow
    0.82
    down
    0.80
    imoto
    0.80
    Activations Density 0.043%

    No Known Activations