© 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. 2480
    Prev
    Next
    INDEX
    Explanations

    quotations or reported speech in the format of '"<text>".'

    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
     behavioral
    -0.74
     centralized
    -0.72
     prioritize
    -0.71
     favored
    -0.71
     willfully
    -0.70
     regress
    -0.70
     maximizing
    -0.69
    imize
    -0.69
     favors
    -0.68
     favor
    -0.67
    POSITIVE LOGITS
     apologised
    1.15
    Mrs
    1.00
     ITV
    0.99
    Shape
    0.97
    Scotland
    0.96
     neighbour
    0.95
    Mr
    0.91
     neighbours
    0.90
     apologise
    0.89
     £
    0.88
    Activations Density 0.537%

    No Known Activations