Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5336
    Prev
    Next
    INDEX
    Explanations

    terms related to technical documentation or management, such as terms related to evaluation, costs, or method

    oai_token-act-pair · gpt-3.5-turbo

    references to administrative structures and management systems

    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
    •Positional
    it seems positional

    No Comments

    Negative Logits
    eday
    -0.54
     wiser
    -0.52
    enegger
    -0.52
    jri
    -0.51
    udos
    -0.50
    staking
    -0.49
     EVEN
    -0.49
     caveat
    -0.48
     pamph
    -0.47
    AAAAAAAA
    -0.47
    POSITIVE LOGITS
    ¶
    0.63
    ratom
    0.61
    zbollah
    0.52
    oplan
    0.50
    ospels
    0.49
    apor
    0.47
    fell
    0.47
    deg
    0.47
    Äģ
    0.46
    âĢIJ
    0.46
    Activations Density 1.419%

    No Known Activations