© 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. 938
    Prev
    Next
    INDEX
    Explanations

    phrases related to the surname "Churchill" and its various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of historical figures, particularly Winston Churchill and Nelson Mandela

    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
    phabet
    -0.80
    Ķ
    -0.77
    imilar
    -0.77
    ĻĤ
    -0.76
    nos
    -0.75
    tle
    -0.71
    Loading
    -0.70
    lated
    -0.70
    stery
    -0.69
    semble
    -0.68
    POSITIVE LOGITS
     Churchill
    1.30
     Downs
    0.99
    igham
    0.82
     Jinn
    0.80
    enstein
    0.77
     Chamberlain
    0.77
     bunker
    0.75
     Browne
    0.74
    espie
    0.74
     commemor
    0.74
    Activations Density 0.006%

    No Known Activations