© 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. 2205
    Prev
    Next
    INDEX
    Explanations

    mentions of financial figures or transactions

    oai_token-act-pair · gpt-3.5-turbo

    the character or symbol "ľ" consistently across different contexts

    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
     manif
    -0.81
     mount
    -0.77
     incorpor
    -0.75
     psychedel
    -0.72
     slic
    -0.72
     synerg
    -0.71
     tyres
    -0.71
     electrodes
    -0.71
     stunts
    -0.70
     tides
    -0.68
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.29
    ï¸ı
    1.29
    âĶĢâĶĢ
    1.18
    âĶĢâĶĢâĶĢâĶĢ
    1.14
    âĸ¬âĸ¬
    1.06
    âĹ
    1.00
    âľ
    0.98
    âĿ
    0.91
    âĢ
    0.90
     âĢº
    0.89
    Activations Density 0.104%

    No Known Activations