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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 12693
    Prev
    Next
    INDEX
    Explanations

    strings within parentheses

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that denote the end of thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    het
    -0.87
    houses
    -0.83
    arest
    -0.73
    gard
    -0.72
    gart
    -0.70
    ihu
    -0.68
    rals
    -0.66
    ton
    -0.65
    shaw
    -0.65
    stones
    -0.65
    POSITIVE LOGITS
    terday
    0.88
    /"
    0.84
    "))
    0.73
    ONSORED
    0.73
    ":[
    0.70
    "],
    0.70
    },{"
    0.69
    ");
    0.68
     fixme
    0.68
    CLAIM
    0.67
    Activations Density 0.011%

    No Known Activations