© 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 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. 19337
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a degree of certainty or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating degrees of uncertainty or ambiguity

    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
     Puzz
    -0.62
    LINE
    -0.60
     Ratings
    -0.60
    ETS
    -0.60
    edia
    -0.58
     Pony
    -0.58
    ocrats
    -0.58
     Novel
    -0.56
     Cipher
    -0.56
    sheets
    -0.55
    POSITIVE LOGITS
    nam
    1.25
    chard
    1.25
    nery
    1.17
    lando
    1.12
    acle
    1.08
    acles
    1.05
    chid
    1.04
    leans
    1.03
    acular
    1.02
    phan
    1.00
    Activations Density 0.068%

    No Known Activations