© 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. 11-RES-JB
    11. 22465
    Prev
    Next
    INDEX
    Explanations

    phrases implying uncertainty or questioning

    oai_token-act-pair · gpt-3.5-turbo

    the character 'Ļ' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kicker
    -0.81
     recycling
    -0.70
     poppy
    -0.69
     hook
    -0.69
     succession
    -0.68
     rolling
    -0.67
     winding
    -0.65
     plum
    -0.65
     Stam
    -0.64
     Garmin
    -0.63
    POSITIVE LOGITS
    ï¸ı
    1.40
    âĢ
    1.19
    ¯¯
    1.18
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.07
    âĹ
    1.07
    âĸł
    1.06
    âĹ¼
    1.06
    âĻ
    1.04
    âĶĢâĶĢâĶĢâĶĢ
    1.03
    âĶĢ
    1.01
    Activations Density 0.224%

    No Known Activations