Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24022
    Prev
    Next
    INDEX
    Explanations

    digital object identifiers (DOIs)

    oai_token-act-pair · gpt-3.5-turbo

    references to Digital Object Identifiers (DOIs) in academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rete
    -0.96
    osta
    -0.77
    cakes
    -0.75
    mbuds
    -0.69
    reet
    -0.66
    board
    -0.65
    trak
    -0.65
    phis
    -0.64
    ibur
    -0.63
    rem
    -0.63
    POSITIVE LOGITS
    doi
    1.40
     DOI
    1.02
     doi
    0.93
     PubMed
    0.92
     Accessed
    0.90
    ://
    0.89
     CrossRef
    0.84
    ="#
    0.82
    romeda
    0.82
    ĸļ
    0.79
    Activations Density 0.035%

    No Known Activations