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. 3-RES-JB
    6. 6773
    Prev
    Next
    INDEX
    Explanations

    terms related to proposing suggestions or theoretical concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to innovative concepts and proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ded
    -0.68
    Naz
    -0.65
    administ
    -0.63
    de
    -0.62
    ords
    -0.61
     Skydragon
    -0.61
    hawks
    -0.59
    DF
    -0.58
    ord
    -0.57
    ady
    -0.56
    POSITIVE LOGITS
     ideas
    0.87
     Ideas
    0.85
    ensical
    0.84
    yout
    0.74
    lip
    0.74
    ilk
    0.71
     underlying
    0.70
    reprene
    0.70
     notions
    0.70
     sugg
    0.70
    Activations Density 0.018%

    No Known Activations