© 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. 6-RES-JB
    11. 658
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations or names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and names associated with various events or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    µ
    -0.68
    士
    -0.66
    Ĺ
    -0.64
    «
    -0.64
    ÄŁ
    -0.63
    ª
    -0.63
    °
    -0.62
    pine
    -0.62
    ·
    -0.61
    ŀ
    -0.61
    POSITIVE LOGITS
    acha
    0.91
    icals
    0.90
    ical
    0.82
    osphere
    0.79
    ned
    0.78
    agne
    0.78
    hedon
    0.76
    onga
    0.74
    ique
    0.74
    ograph
    0.73
    Activations Density 0.084%

    No Known Activations