© 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. 19871
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Moss"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Moss"

    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
     conv
    -0.73
     shutdown
    -0.69
     âĸº
    -0.67
    acon
    -0.66
     interrupt
    -0.66
     shut
    -0.65
    èª
    -0.64
     impulse
    -0.64
    lator
    -0.63
     async
    -0.63
    POSITIVE LOGITS
     Moss
    4.19
     moss
    1.73
     Ness
    1.22
     Marsh
    1.13
     Morton
    1.13
     Mos
    1.11
     Herz
    1.07
     Mush
    1.06
     Hamm
    1.05
     Rothschild
    1.05
    Activations Density 0.018%

    No Known Activations