© 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. 17865
    Prev
    Next
    INDEX
    Explanations

    verbs related to planning, preparing, pushing, trying, partnering, and mulling

    oai_token-act-pair · gpt-3.5-turbo

    actions related to advocacy and preparation

    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
    sac
    -0.73
    worthiness
    -0.66
    ritical
    -0.65
    croft
    -0.65
    ijk
    -0.65
    tes
    -0.64
    âĢij
    -0.61
     preceding
    -0.60
    tra
    -0.60
    rouse
    -0.60
    POSITIVE LOGITS
     ducks
    0.69
     furiously
    0.65
     developments
    0.63
     preparations
    0.63
    redients
    0.61
    irection
    0.60
    ITAL
    0.60
     frantically
    0.59
    igated
    0.59
     proactive
    0.59
    Activations Density 0.293%

    No Known Activations