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. 4-RES-JB
    6. 3522
    Prev
    Next
    INDEX
    Explanations

    words/phrases/acronyms within single quotation marks (" ") or specific characters ('Ċ', 'Ļ', 'âĢ' etc.)

    oai_token-act-pair · gpt-3.5-turbo

    references to significant political events or figures

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

    No Comments

    Negative Logits
     endeavour
    -0.99
     enqu
    -0.86
     realised
    -0.82
     endeav
    -0.80
     Reincarnated
    -0.77
     realise
    -0.75
     regenerate
    -0.75
     practise
    -0.74
     tyres
    -0.72
    itary
    -0.72
    POSITIVE LOGITS
    Asked
    1.19
    Washington
    1.17
    Republicans
    1.11
    Republican
    1.10
    Bill
    1.07
    Congress
    1.04
    Clinton
    1.04
    Critics
    1.04
    President
    1.03
    Wisconsin
    1.03
    Activations Density 0.839%

    No Known Activations