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. 4013
    Prev
    Next
    INDEX
    Explanations

    claims or statistics made by survey respondents

    oai_token-act-pair · gpt-3.5-turbo

    statistical data regarding public opinion or survey results

    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
    forth
    -0.79
    cour
    -0.66
    chemy
    -0.63
    eers
    -0.62
    Bytes
    -0.60
    ãĥ¯
    -0.60
     Commodore
    -0.59
     beck
    -0.58
     carnage
    -0.58
    oux
    -0.58
    POSITIVE LOGITS
     personally
    1.00
     unfavorable
    0.95
     disapprove
    0.93
     Somew
    0.93
     favorably
    0.90
     unsure
    0.89
    agree
    0.88
     respondents
    0.83
     satisfied
    0.82
     Unsure
    0.82
    Activations Density 0.251%

    No Known Activations