© 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. 17436
    Prev
    Next
    INDEX
    Explanations

    words related to celebrities and famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of characters and places in fictional contexts

    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
     Calder
    -0.58
     herald
    -0.58
     Bett
    -0.57
     logging
    -0.56
    started
    -0.56
     endowed
    -0.56
     Clover
    -0.55
     imperative
    -0.55
     Pell
    -0.55
     sterling
    -0.55
    POSITIVE LOGITS
    pta
    1.06
    oku
    0.86
    ecast
    0.85
    atchewan
    0.82
    ivas
    0.81
    atoon
    0.80
    oslav
    0.77
    anka
    0.76
    inx
    0.76
    omore
    0.74
    Activations Density 0.117%

    No Known Activations