© 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. 3-RES-JB
    11. 3766
    Prev
    Next
    INDEX
    Explanations

    the specific word "anytime"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "anytime" in various contexts

    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
    asts
    -0.76
    iv
    -0.75
    harm
    -0.72
    riks
    -0.71
    atively
    -0.70
    uers
    -0.70
    abal
    -0.69
    rog
    -0.69
    aos
    -0.69
    erie
    -0.69
    POSITIVE LOGITS
    soever
    1.07
    theless
    1.01
     else
    0.92
    THING
    0.87
    £ı
    0.79
     remotely
    0.74
     UTC
    0.73
    ĸļ
    0.72
    entimes
    0.70
    dayName
    0.70
    Activations Density 0.004%

    No Known Activations