Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2134
    Prev
    Next
    INDEX
    Explanations

    references to technology

    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
    )?
    -0.78
    ]).
    -0.73
    )))
    -0.72
    )).
    -0.70
     ])
    -0.70
    ?ãĢį
    -0.69
     ?)
    -0.69
     ))
    -0.68
     attRot
    -0.66
     )))
    -0.66
    POSITIVE LOGITS
     wherever
    0.76
     whereas
    0.74
     effortlessly
    0.66
     and
    0.66
     beautifully
    0.65
     alongside
    0.64
     throughout
    0.64
     while
    0.63
    lessly
    0.61
     faithfully
    0.61
    Activations Density 1.177%

    No Known Activations