© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2778
    Prev
    Next
    INDEX
    Explanations

    words related to previously existing entities or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to previous individuals or roles in a hierarchy

    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
     Ukrain
    -0.75
    erer
    -0.72
    oros
    -0.70
    awar
    -0.67
     Butcher
    -0.65
    rophe
    -0.62
     Overt
    -0.62
    bel
    -0.61
     Population
    -0.61
    Pak
    -0.60
    POSITIVE LOGITS
     predecessors
    0.72
    sonian
    0.71
    姫
    0.70
     styled
    0.70
    arios
    0.69
    ptions
    0.69
    cules
    0.68
    hood
    0.67
    ptive
    0.66
    pection
    0.66
    Activations Density 0.023%

    No Known Activations