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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 18491
    Prev
    Next
    INDEX
    Explanations

    phrases related to data analysis and research

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whenever
    -0.81
    heit
    -0.77
     instead
    -0.74
    .</
    -0.72
     whilst
    -0.71
    umbing
    -0.71
    .","
    -0.71
    .
    -0.71
    !.
    -0.71
     because
    -0.70
    POSITIVE LOGITS
     latter
    1.09
     aforementioned
    1.01
    ses
    0.96
     nutshell
    0.90
     foregoing
    0.89
     initial
    0.80
     latest
    0.79
    oret
    0.78
     remainder
    0.75
     greatest
    0.75
    Activations Density 0.649%

    No Known Activations