© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 6220
    Prev
    Next
    INDEX
    Explanations

    words related to actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    verbs or gerunds that indicate active or ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipedia
    -0.84
    emetery
    -0.84
    OIL
    -0.80
    poll
    -0.80
    answer
    -0.77
    çĦ
    -0.77
    IFIED
    -0.76
    ãģ£
    -0.74
    IFE
    -0.74
    éĸ
    -0.73
    POSITIVE LOGITS
     extraord
    0.98
     spree
    0.93
     antics
    0.91
    tons
    0.86
     machines
    0.85
     tendencies
    0.84
     robots
    0.83
     zeal
    0.82
     stunts
    0.80
     activities
    0.77
    Activations Density 0.148%

    No Known Activations