© 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. 9-RES-JB
    11. 5241
    Prev
    Next
    INDEX
    Explanations

    references to the philosophical and moral concept of altruism

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating disbelief or negativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pyramid
    -0.72
     recycling
    -0.71
     lodging
    -0.65
     succession
    -0.65
     shifts
    -0.65
     recall
    -0.65
     literacy
    -0.63
     decom
    -0.63
     logger
    -0.61
     exposures
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.50
    âĶĢâĶĢâĶĢâĶĢ
    1.22
    ¯¯
    1.17
    âĻ
    1.10
    ¯
    1.09
    âĶĢ
    0.99
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.98
    âĶ
    0.95
    ¯¯¯¯
    0.95
    âĤ¬
    0.93
    Activations Density 0.323%

    No Known Activations