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. 2-RES-JB
    6. 22659
    Prev
    Next
    INDEX
    Explanations

    file names or file-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to files, particularly in the context of downloading and accessing digital content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patron
    -0.73
    south
    -0.66
    orical
    -0.65
    ozy
    -0.64
     apartheid
    -0.62
    odor
    -0.62
     coastal
    -0.61
    egal
    -0.60
     Poly
    -0.60
     Labor
    -0.60
    POSITIVE LOGITS
    ystem
    1.42
    uggest
    1.07
    paces
    1.06
    heet
    0.98
     files
    0.97
    uits
    0.93
    pace
    0.93
    mith
    0.93
     downloaded
    0.92
    ynthesis
    0.92
    Activations Density 0.009%

    No Known Activations