© 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. 10443
    Prev
    Next
    INDEX
    Explanations

    phrases related to work, tasks, or actions

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented phrases indicating activities or functions

    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
     ðŁĻĤ
    -0.78
     âĢ¦"
    -0.74
    âĢ¦âĢ¦
    -0.71
    âĢ¦"
    -0.69
    âĢķ
    -0.66
     ðŁĺ
    -0.66
    —"
    -0.64
     ;)
    -0.64
     ðŁ
    -0.64
    Ïī
    -0.63
    POSITIVE LOGITS
    quartered
    1.21
    entimes
    0.94
    sequently
    0.93
    neath
    0.91
    icularly
    0.90
    ificantly
    0.88
     Locations
    0.87
    sequent
    0.87
    ensibly
    0.85
    inarily
    0.84
    Activations Density 0.338%

    No Known Activations