© 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. 0-RES-JB
    11. 6658
    Prev
    Next
    INDEX
    Explanations

    obscure or rare words

    oai_token-act-pair · gpt-3.5-turbo

    references to uncommon or elusive concepts and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.71
     welcomes
    -0.69
     Plus
    -0.65
    payers
    -0.64
    Fin
    -0.62
    ®
    -0.61
     Participation
    -0.61
     Response
    -0.61
     Owner
    -0.60
    amide
    -0.60
    POSITIVE LOGITS
     obscure
    3.66
     obscurity
    2.04
     obscured
    1.58
     esoteric
    1.55
     arcane
    1.43
     obsc
    1.37
     cryptic
    1.25
    unknown
    1.25
     murky
    1.25
     obfusc
    1.24
    Activations Density 0.018%

    No Known Activations