© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 6525
    Prev
    Next
    INDEX
    Explanations

    instances where the word "want" is used

    oai_token-act-pair · gpt-3.5-turbo

    requests or expressions of desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.72
    eding
    -0.68
    VERTISEMENT
    -0.68
    ammy
    -0.67
    semble
    -0.65
    SPONSORED
    -0.64
    fell
    -0.63
    uum
    -0.62
    cession
    -0.61
    è¦ļéĨĴ
    -0.61
    POSITIVE LOGITS
    reprene
    0.96
    urities
    0.90
    htar
    0.67
     to
    0.66
    atis
    0.65
     warr
    0.63
    anamo
    0.61
     want
    0.61
    atem
    0.61
     extrad
    0.60
    Activations Density 0.068%

    No Known Activations