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

    Neuronpedia

    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. 4-RES-JB
    11. 19805
    Prev
    Next
    INDEX
    Explanations

    phrases related to examining or investigating something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "examine" and its variations in context

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

    No Comments

    Negative Logits
    gren
    -0.74
    âĹ¼
    -0.72
    cil
    -0.67
     damned
    -0.64
    activated
    -0.63
    loaded
    -0.63
    fires
    -0.63
    die
    -0.62
     hire
    -0.62
    cell
    -0.61
    POSITIVE LOGITS
    ĸļ
    0.96
    ively
    0.90
    mble
    0.83
    ury
    0.82
    emouth
    0.81
    osterone
    0.79
     Probe
    0.78
    xual
    0.78
     examines
    0.75
    alus
    0.75
    Activations Density 0.020%

    No Known Activations