© 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. 19801
    Prev
    Next
    INDEX
    Explanations

    references to trophies or awards

    oai_token-act-pair · gpt-3.5-turbo

    mentions of trophies in various contexts, emphasizing their significance and prevalence

    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
    Ur
    -0.78
     Alter
    -0.77
     Zeit
    -0.68
     Burlington
    -0.67
    called
    -0.66
    omsky
    -0.63
    apesh
    -0.63
     Blink
    -0.63
     Ur
    -0.61
    rise
    -0.61
    POSITIVE LOGITS
     trophy
    3.94
     trophies
    3.40
     Trophy
    2.44
    phies
    1.97
     medal
    1.36
     prize
    1.35
     medals
    1.28
     souven
    1.20
     bragging
    1.15
     prizes
    1.13
    Activations Density 0.020%

    No Known Activations