© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 3711
    Prev
    Next
    INDEX
    Explanations

    phrases indicating start or beginning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to events, their timing, and durations

    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
     hesitate
    -0.68
     manoeuv
    -0.66
    anyon
    -0.64
     clipboard
    -0.64
    Reviewer
    -0.62
    oult
    -0.61
     manually
    -0.61
     glide
    -0.61
    ettel
    -0.60
    %;
    -0.60
    POSITIVE LOGITS
    ONSORED
    0.79
    sole
    0.76
    tained
    0.73
    CLUD
    0.71
    days
    0.70
    ersed
    0.68
     Supplement
    0.68
     SDL
    0.67
    tains
    0.67
    actionDate
    0.66
    Activations Density 0.556%

    No Known Activations