© 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. 4-RES-JB
    11. 19393
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'm'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the mention of specific times written in the format of hours and minutes followed by "p.m."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Atlantis
    -0.69
     Analog
    -0.69
     Bubble
    -0.66
     XIII
    -0.61
     Shall
    -0.61
     Behavior
    -0.61
     Toast
    -0.60
     straw
    -0.60
     Wast
    -0.60
     scratched
    -0.59
    POSITIVE LOGITS
    iles
    0.98
    igr
    0.97
    endment
    0.92
    ichael
    0.91
    obiles
    0.88
    eredith
    0.87
    oses
    0.86
    onday
    0.85
     ILCS
    0.85
    ansion
    0.84
    Activations Density 0.018%

    No Known Activations