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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20244
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantity or magnitude

    oai_token-act-pair · gpt-3.5-turbo

    frequent uses of the phrase "a lot of."

    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
    ħĭ
    -0.92
    ĸļ
    -0.87
    most
    -0.87
    acus
    -0.83
    gypt
    -0.80
    era
    -0.77
    acle
    -0.76
    edience
    -0.73
    uthor
    -0.72
    ade
    -0.71
    POSITIVE LOGITS
     stuff
    1.02
     fun
    1.02
     goodies
    0.99
     things
    0.97
     crap
    0.92
     unanswered
    0.91
     surprises
    0.91
     interesting
    0.88
     positives
    0.88
     juicy
    0.87
    Activations Density 0.101%

    No Known Activations