© 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. 3903
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to individuals named "Len" or "Lenovo"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Len" and related variations

    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
    xual
    -0.70
     Seeking
    -0.68
     Occupations
    -0.66
    tale
    -0.65
    milo
    -0.64
    rious
    -0.63
    fly
    -0.62
     Debor
    -0.62
    schild
    -0.62
    annot
    -0.61
    POSITIVE LOGITS
     Len
    0.93
    ovo
    0.87
    uci
    0.86
    iency
    0.86
    seys
    0.82
    gement
    0.79
    apse
    0.77
    terness
    0.75
    minster
    0.75
    apses
    0.75
    Activations Density 0.006%

    No Known Activations