© 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. 11-RES-JB
    11. 7119
    Prev
    Next
    INDEX
    Explanations

    titles, headings, or labels within a document

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jagu
    -0.83
    467
    -0.82
     SolidGoldMagikarp
    -0.81
     1947
    -0.80
     Invaders
    -0.79
     Kira
    -0.79
    ault
    -0.78
     Kra
    -0.77
     Archer
    -0.77
     Lich
    -0.75
    POSITIVE LOGITS
    10
    1.46
     10
    1.29
     1070
    1.09
    2010
    1.07
    1027
    1.02
     ten
    0.97
    102
    0.96
     1050
    0.94
     2010
    0.94
    1024
    0.93
    Activations Density 0.439%

    No Known Activations