© 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. 6-RES-JB
    11. 7532
    Prev
    Next
    INDEX
    Explanations

    words related to the composer Beethoven, particularly focusing on occurrences of the spelling "eth" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the composer Beethoven

    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
     Clement
    -0.74
    enhagen
    -0.71
    éĹĺ
    -0.70
    yrinth
    -0.69
    xual
    -0.66
     referen
    -0.61
     takedown
    -0.61
    ratulations
    -0.61
    aution
    -0.59
    eers
    -0.59
    POSITIVE LOGITS
    lehem
    1.41
    amphetamine
    1.12
    iop
    1.12
    ulhu
    1.03
    anol
    0.98
    rower
    0.96
    icone
    0.93
    ought
    0.91
    yll
    0.90
    anasia
    0.87
    Activations Density 0.023%

    No Known Activations