© 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. 3-RES-JB
    11. 10769
    Prev
    Next
    INDEX
    Explanations

    keywords related to historical events or political topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty or filler text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raints
    -0.76
    matic
    -0.71
    urated
    -0.68
     Instr
    -0.68
     condem
    -0.65
     monop
    -0.65
    ciating
    -0.63
    enegger
    -0.62
     primates
    -0.60
     apes
    -0.59
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.13
    ï¸ı
    1.06
    uthor
    0.86
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.83
    ĺ
    0.82
    ×Ķ
    0.82
    âĢł
    0.82
    ļ
    0.80
    fter
    0.79
    âĸł
    0.78
    Activations Density 0.201%

    No Known Activations