© 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. 10-RES-JB
    11. 12846
    Prev
    Next
    INDEX
    Explanations

    instances of tab character followed by sequences of recurring characters

    oai_token-act-pair · gpt-3.5-turbo

    representations of numbers or numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     torpedo
    -0.84
     coral
    -0.78
     trave
    -0.77
     tyres
    -0.77
     metic
    -0.77
     overlapping
    -0.76
     fancy
    -0.75
     dynam
    -0.75
     mushroom
    -0.75
     favoured
    -0.75
    POSITIVE LOGITS
    âĢ
    1.87
    Advertisements
    1.62
    Thank
    1.46
    Translation
    1.45
    âĺ
    1.44
    Comments
    1.44
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.43
    âĶ
    1.42
    (*
    1.41
    âĿ
    1.40
    Activations Density 0.353%

    No Known Activations