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. 9-RES-JB
    6. 227
    Prev
    Next
    INDEX
    Explanations

    specific terms or keywords related to legal, political, and military contexts, such as "Predicated", "Declaration", "Complaint", and "Opposition"

    oai_token-act-pair · gpt-3.5-turbo

    instances of distinct Pokémon characteristics or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blah
    -0.79
     â̦"
    -0.70
     shield
    -0.69
     wool
    -0.69
    Ïī
    -0.68
     polyg
    -0.66
     DRAG
    -0.66
     metab
    -0.66
     Frie
    -0.65
     pow
    -0.65
    POSITIVE LOGITS
    roximately
    1.25
    vertising
    1.19
    initions
    1.12
    reprene
    1.12
    withstanding
    1.12
    inarily
    1.11
    ilities
    1.11
    resa
    1.09
    iction
    1.08
    rary
    1.08
    Activations Density 0.188%

    No Known Activations