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. 3-RES-JB
    6. 19737
    Prev
    Next
    INDEX
    Explanations

    dates written with a slash in the format month/day/year

    oai_token-act-pair · gpt-3.5-turbo

    structured numerical data or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lumpur
    -0.87
    awaru
    -0.82
    thinkable
    -0.70
     vel
    -0.69
    ufact
    -0.68
    ategory
    -0.68
    apon
    -0.66
    usalem
    -0.65
     roofs
    -0.64
     WATCHED
    -0.62
    POSITIVE LOGITS
    Password
    1.23
    125
    1.21
    120
    1.17
    st
    1.15
    000000
    1.11
    128
    1.01
    0000000
    0.99
    123
    0.87
    GB
    0.82
    00000000
    0.82
    Activations Density 0.098%

    No Known Activations