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. 11-RES-JB
    6. 2864
    Prev
    Next
    INDEX
    Explanations

    statements about the potential or performance of individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate possession or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entary
    -0.77
    wait
    -0.72
     Refer
    -0.71
    uating
    -0.68
    ocide
    -0.66
     Consult
    -0.66
    USE
    -0.65
    FL
    -0.64
     Coffin
    -0.63
     Recap
    -0.63
    POSITIVE LOGITS
     been
    1.23
     gotten
    1.22
     proven
    1.22
     matured
    1.19
     flourished
    1.17
     succeeded
    1.16
     achieved
    1.15
     mastered
    1.14
     risen
    1.14
     earned
    1.13
    Activations Density 0.238%

    No Known Activations