© 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. 8-RES-JB
    11. 505
    Prev
    Next
    INDEX
    Explanations

    locations or entities with a focus on the present time

    oai_token-act-pair · gpt-3.5-turbo

    references to current status or ongoing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     similarity
    -0.69
     otherwise
    -0.64
     bells
    -0.63
     avoidance
    -0.61
     initially
    -0.60
     beforehand
    -0.58
     meantime
    -0.58
     brav
    -0.58
     earlier
    -0.58
     originally
    -0.57
    POSITIVE LOGITS
    Reviewer
    0.73
    ģĸ
    0.71
    YL
    0.68
    Ô
    0.68
    here
    0.68
    YR
    0.67
    enium
    0.66
    hops
    0.64
    ocene
    0.64
    sylvania
    0.63
    Activations Density 0.323%

    No Known Activations