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. 6-RES-JB
    6. 8338
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs related to intensity or strength

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "verify" or related concepts of verification

    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
    ENDED
    -0.74
    »Ĵ
    -0.70
     Towns
    -0.69
    ered
    -0.68
    NetMessage
    -0.66
    emi
    -0.66
     Rh
    -0.65
    ENS
    -0.64
     Fever
    -0.64
     Sparrow
    -0.63
    POSITIVE LOGITS
    ifiable
    1.13
    itable
    1.08
    ulent
    1.03
    bat
    0.94
    ulence
    0.91
    anda
    0.90
    itably
    0.89
    gue
    0.89
    istically
    0.89
    bal
    0.89
    Activations Density 0.013%

    No Known Activations