© 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. 1-RES-JB
    11. 8705
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to famous personalities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly the name "Morrison."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.77
    ×IJ
    -0.77
    ×Ķ
    -0.76
    lihood
    -0.72
     Nir
    -0.72
    è¯
    -0.71
    fare
    -0.70
    BOOK
    -0.68
    UAL
    -0.65
     Settlement
    -0.65
    POSITIVE LOGITS
     Morrison
    1.26
    rison
    1.18
    quist
    0.90
     Leilan
    0.84
    inson
    0.81
    igon
    0.78
    shire
    0.75
    ufact
    0.74
     crossings
    0.74
    vernment
    0.74
    Activations Density 0.004%

    No Known Activations