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. 12-RES-JB
    6. 15160
    Prev
    Next
    INDEX
    Explanations

    information related to community development and social programs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to community facilities and social support structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ¬¼
    -0.78
    itone
    -0.73
    ":"/
    -0.72
    vale
    -0.71
    ģĸ
    -0.68
    ioxide
    -0.67
    iatrics
    -0.67
    KEN
    -0.66
    ãĥĥãĥĪ
    -0.65
    elta
    -0.64
    POSITIVE LOGITS
     namely
    1.37
     including
    1.27
     whereas
    1.27
     which
    1.23
     whereby
    1.23
     wherein
    1.21
     although
    1.13
     however
    1.07
     but
    1.03
     albeit
    1.01
    Activations Density 0.391%

    No Known Activations