© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14794
    Prev
    Next
    INDEX
    Explanations

    proper nouns with 'Win' as a prefix

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Windows operating system and its 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
    ħĭ
    -0.73
     condu
    -0.73
    âĶģ
    -0.70
     destro
    -0.67
    orescent
    -0.66
    umn
    -0.66
    OAD
    -0.66
     Uz
    -0.66
    ĸļ
    -0.65
     UCHIJ
    -0.63
    POSITIVE LOGITS
    ners
    1.25
    win
    1.06
    frey
    1.04
    fred
    0.93
    nings
    0.88
    ning
    0.87
    throp
    0.86
    kees
    0.86
    amac
    0.85
    ston
    0.85
    Activations Density 0.010%

    No Known Activations