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. 14311
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantities denoted with a hyphen and number such as 'two-9'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "two-" in various contexts

    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
     Canaver
    -0.71
     BDS
    -0.66
    ulhu
    -0.66
    gerald
    -0.63
     Clyde
    -0.62
     Lovecraft
    -0.62
    essor
    -0.62
     Rica
    -0.59
     Shaw
    -0.59
     Gillespie
    -0.59
    POSITIVE LOGITS
    thirds
    1.47
    dimensional
    1.08
    legged
    1.05
    income
    1.04
    hander
    1.03
    digit
    1.01
     thirds
    0.99
    tailed
    0.99
    degree
    0.98
    year
    0.98
    Activations Density 0.043%

    No Known Activations