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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2471
    Prev
    Next
    INDEX
    Explanations

    time references in a specific format - hours followed by 'a.m.' or 'p.m.'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'm'

    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
    -0.64
    DragonMagazine
    -0.58
     acknowled
    -0.54
     blink
    -0.53
     behav
    -0.53
     apartheid
    -0.52
     conson
    -0.51
     literature
    -0.51
     disob
    -0.50
     spare
    -0.50
    POSITIVE LOGITS
    .,
    1.80
    .;
    1.62
    .?
    1.54
    .:
    1.49
    .,"
    1.45
    ./
    1.34
    .–
    1.27
    .—
    1.25
    .-
    1.23
    .),
    1.21
    Activations Density 0.020%

    No Known Activations