© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 17317
    Prev
    Next
    INDEX
    Explanations

    temporal information related to time periods and averages

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and average values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jah
    -0.56
    ggle
    -0.52
    raft
    -0.48
    DEN
    -0.47
    hib
    -0.47
    lash
    -0.47
    rium
    -0.46
    Emb
    -0.46
    gypt
    -0.45
    Loading
    -0.45
    POSITIVE LOGITS
     notwithstanding
    0.51
    ãĥĩãĤ£
    0.46
    arently
    0.44
     apologies
    0.43
     phr
    0.43
     preferring
    0.43
     bip
    0.41
     practition
    0.41
     Nanto
    0.41
     preferably
    0.41
    Activations Density 1.480%

    No Known Activations