© 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. 22271
    Prev
    Next
    INDEX
    Explanations

    phrases or names that are famous or well-known

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "famously" and its variations, indicating notable achievements or reputations

    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
    orate
    -0.65
     EVENTS
    -0.65
    Spons
    -0.64
    ipal
    -0.64
    Spread
    -0.62
    taboola
    -0.62
    ~~~~
    -0.60
     persons
    -0.59
    Amount
    -0.59
    /-
    -0.59
    POSITIVE LOGITS
     famously
    3.09
     notoriously
    2.43
     notably
    2.23
     controvers
    1.54
     noticeably
    1.47
     predictably
    1.36
     surprisingly
    1.31
     remarkably
    1.31
     conspic
    1.29
     shockingly
    1.25
    Activations Density 0.019%

    No Known Activations