© 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. 22578
    Prev
    Next
    INDEX
    Explanations

    phrases expressing certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to ambiguous or undefined terms and concepts

    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
     Seym
    -0.65
     carbohyd
    -0.63
     mathemat
    -0.61
     vulner
    -0.61
     disadvant
    -0.60
     exha
    -0.55
     hemor
    -0.54
     philos
    -0.52
     contrace
    -0.52
     fragmentation
    -0.51
    POSITIVE LOGITS
    ï¸ı
    0.88
    £
    0.66
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.66
    ¯
    0.61
    ï¸
    0.61
    ATH
    0.61
    âĶĢâĶĢ
    0.61
    ±
    0.61
    ·
    0.61
    âĵĺ
    0.60
    Activations Density 0.686%

    No Known Activations