© 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. 13587
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific points in time or periods

    oai_token-act-pair · gpt-3.5-turbo

    the presence of end-of-text tokens

    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
    ornings
    -0.59
    emale
    -0.59
    herer
    -0.58
     beforehand
    -0.56
    *.
    -0.55
    /"
    -0.53
     afterwards
    -0.53
    ÃĥÃĤ
    -0.52
     conclud
    -0.52
     theirs
    -0.52
    POSITIVE LOGITS
     same
    0.77
    oret
    0.74
    resa
    0.73
     simplest
    0.73
     hottest
    0.72
     latest
    0.71
     following
    0.70
     largest
    0.70
     foregoing
    0.70
    ses
    0.70
    Activations Density 0.918%

    No Known Activations