© 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. 10-RES-JB
    11. 21780
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or places, primarily focusing on surnames

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILY
    -0.75
    verning
    -0.69
     resil
    -0.68
    ãģŁ
    -0.66
    ptive
    -0.65
    BLE
    -0.64
    behind
    -0.62
    STON
    -0.61
     homeland
    -0.61
    ACY
    -0.60
    POSITIVE LOGITS
    sov
    1.24
    own
    1.14
    chev
    1.07
    ronics
    1.05
    ooth
    1.03
    ting
    1.00
    ilde
    0.99
    te
    0.98
    ty
    0.98
    opia
    0.97
    Activations Density 0.119%

    No Known Activations