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. 4426
    Prev
    Next
    INDEX
    Explanations

    phrases related to different attributes or aspects of a community or organization, such as defense, storylines, general relations, infrastructure, and manufacturing sectors

    oai_token-act-pair · gpt-3.5-turbo

    references to defense and community relationships

    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
    but
    -0.91
     but
    -0.68
    hex
    -0.61
    emate
    -0.61
     But
    -0.60
     suffice
    -0.59
    ©¶æ
    -0.59
    £ı
    -0.58
    SpaceEngineers
    -0.58
    until
    -0.58
    POSITIVE LOGITS
     itself
    1.20
     themselves
    0.97
    !:
    0.86
     too
    0.84
     oneself
    0.82
     herself
    0.78
     himself
    0.76
    !
    0.74
     Himself
    0.74
    .:
    0.73
    Activations Density 0.964%

    No Known Activations