© 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. 7-RES-JB
    11. 5360
    Prev
    Next
    INDEX
    Explanations

    phrases describing the purpose or aim of different activities or projects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate purpose or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ashtra
    -0.84
    aults
    -0.76
    dayName
    -0.75
    Crash
    -0.71
    rimp
    -0.70
    isms
    -0.70
    thur
    -0.69
    frog
    -0.69
    rums
    -0.67
    artifacts
    -0.64
    POSITIVE LOGITS
    interstitial
    0.76
     provoking
    0.76
     determining
    0.75
     preserving
    0.75
     establishing
    0.68
     constructing
    0.67
     maximizing
    0.66
     investing
    0.65
     inducing
    0.65
     arrang
    0.64
    Activations Density 0.083%

    No Known Activations