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. 0-RES-JB
    6. 17572
    Prev
    Next
    INDEX
    Explanations

    dates or time references in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related designations or tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sounding
    -0.69
     leather
    -0.66
     head
    -0.64
     Grimm
    -0.64
     sound
    -0.63
     gl
    -0.62
     apples
    -0.62
     lur
    -0.62
     Dun
    -0.62
     Heat
    -0.62
    POSITIVE LOGITS
    PT
    4.63
    pt
    1.70
     PT
    1.56
    PP
    1.49
    MT
    1.44
    BT
    1.30
    PE
    1.26
    PD
    1.25
    PM
    1.23
    CT
    1.22
    Activations Density 0.005%

    No Known Activations