© 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. 9-RES-JB
    11. 9130
    Prev
    Next
    INDEX
    Explanations

    Words related to successful performance or high achievement, particularly in terms of financial success

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzle
    -0.79
     Helpful
    -0.70
     Doodle
    -0.69
     Roof
    -0.67
     Seasons
    -0.65
     Retro
    -0.64
    cale
    -0.64
     Beard
    -0.64
     Wedding
    -0.64
     Chak
    -0.63
    POSITIVE LOGITS
    -
    0.81
     brig
    0.80
    busters
    0.79
    âĢij
    0.77
    sharing
    0.74
    brand
    0.71
    trak
    0.67
    gas
    0.67
    gang
    0.66
    runners
    0.65
    Activations Density 0.471%

    No Known Activations