© 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. 9089
    Prev
    Next
    INDEX
    Explanations

    abstract phenomena or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "phenomenon" and related terms

    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
    gur
    -0.77
    zar
    -0.74
    oÄŁ
    -0.68
    endar
    -0.68
    ACTED
    -0.68
    ardless
    -0.66
    zie
    -0.66
    har
    -0.66
    gements
    -0.65
    ãĤĮ
    -0.65
    POSITIVE LOGITS
     occurring
    1.07
     whereby
    1.02
     Known
    0.92
     occurrence
    0.92
    ually
    0.90
    icity
    0.87
     phenomena
    0.87
     unfolding
    0.85
     phenomenon
    0.85
     occ
    0.83
    Activations Density 0.063%

    No Known Activations