© 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. 10-RES-JB
    11. 11366
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to taking action or suggesting involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     independ
    -0.83
    `.
    -0.81
    Advertisements
    -0.80
     Whilst
    -0.76
    ´
    -0.75
     doesnt
    -0.74
    ________________________________________________________________
    -0.73
    ********************************
    -0.72
    Firstly
    -0.72
     whilst
    -0.71
    POSITIVE LOGITS
    Enlarge
    0.83
    —"
    0.82
     Rodham
    0.70
    toggle
    0.68
     —
    0.65
     persuaded
    0.65
     Giuliani
    0.64
    —
    0.63
     Suppose
    0.63
     Cohn
    0.61
    Activations Density 1.250%

    No Known Activations