© 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. 4-RES-JB
    11. 1261
    Prev
    Next
    INDEX
    Explanations

    verbs related to a specific action being directed towards a particular goal or target

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating aims or objectives

    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
    glass
    -0.71
    ten
    -0.70
    bite
    -0.67
    alpha
    -0.67
    changed
    -0.66
    blade
    -0.65
    arch
    -0.64
    fill
    -0.64
    owner
    -0.64
    shell
    -0.63
    POSITIVE LOGITS
     least
    1.01
    onement
    0.93
    abase
    0.86
    ĸļ
    0.84
     halftime
    0.83
    roph
    0.77
    è¦ļéĨĴ
    0.76
     risk
    0.74
    omics
    0.73
    rial
    0.73
    Activations Density 0.125%

    No Known Activations