© 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. 5214
    Prev
    Next
    INDEX
    Explanations

    references to different countries, cities, and travel-related terms

    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
    Reviewer
    -0.59
     Aval
    -0.49
     indeed
    -0.44
     prefix
    -0.42
     lightly
    -0.41
     "#
    -0.41
     accredited
    -0.39
     bounded
    -0.39
     VERS
    -0.39
     Paddock
    -0.39
    POSITIVE LOGITS
     thereof
    0.60
    cellaneous
    0.57
    undai
    0.56
    anta
    0.55
    oultry
    0.52
     thereto
    0.51
     versa
    0.50
    Į
    0.49
    sequent
    0.49
    ĭ
    0.48
    Activations Density 0.816%

    No Known Activations