© 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. 18662
    Prev
    Next
    INDEX
    Explanations

    links or references of continuation instructions

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to continuing or following instructions

    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
    aird
    -0.63
    ktop
    -0.61
    nce
    -0.61
    pard
    -0.60
    tn
    -0.57
    anchester
    -0.57
    aspx
    -0.56
    Taylor
    -0.56
    rame
    -0.55
    emet
    -0.55
    POSITIVE LOGITS
    çĶ°
    0.85
    anwhile
    0.69
    HI
    0.67
    ¥µ
    0.63
    aic
    0.62
    ãĥĭ
    0.62
     Metatron
    0.61
    ãĥ«
    0.60
     Spoiler
    0.59
    ãĥ©ãĥ³
    0.58
    Activations Density 0.198%

    No Known Activations