© 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. 2798
    Prev
    Next
    INDEX
    Explanations

    words related to achievements or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of awards and winning achievements

    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
     ig
    -0.74
     mol
    -0.67
     dis
    -0.67
     gas
    -0.66
     cal
    -0.65
     charges
    -0.65
     mixed
    -0.64
     inter
    -0.63
     Mesh
    -0.63
     concealed
    -0.63
    POSITIVE LOGITS
    winning
    4.00
    winner
    2.82
     Winning
    1.77
     winning
    1.76
    Winner
    1.57
    nom
    1.52
    win
    1.51
     winner
    1.42
    Win
    1.34
     winners
    1.19
    Activations Density 0.010%

    No Known Activations