© 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. 9242
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons or ratios

    oai_token-act-pair · gpt-3.5-turbo

    quantifiers related to the concept of 'each' and 'every'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    mare
    -0.73
    ved
    -0.68
     Activate
    -0.66
    cheat
    -0.64
    glers
    -0.63
    edin
    -0.63
    Cho
    -0.63
    mosp
    -0.62
    rien
    -0.62
    xon
    -0.61
    POSITIVE LOGITS
     sake
    1.80
     purposes
    1.54
     reasons
    1.19
    ummies
    1.12
     purpose
    1.01
     foreseeable
    0.85
     upcoming
    0.83
     reason
    0.82
     Reasons
    0.75
    umption
    0.75
    Activations Density 0.467%

    No Known Activations