© 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. 2-RES-JB
    11. 1473
    Prev
    Next
    INDEX
    Explanations

    proper names like "Boyle" and "Higgins"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneous
    -0.87
    ilage
    -0.82
    hra
    -0.79
    onym
    -0.78
    NAS
    -0.77
     drawer
    -0.74
    azeera
    -0.73
    ublic
    -0.72
    onyms
    -0.71
    elo
    -0.71
    POSITIVE LOGITS
    ynski
    0.86
     Higgins
    0.79
     Remastered
    0.78
    ï¸ı
    0.77
    yip
    0.75
    abad
    0.74
     nodd
    0.74
    shed
    0.74
    ongyang
    0.73
    s
    0.72
    Activations Density 0.024%

    No Known Activations