© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 11779
    Prev
    Next
    INDEX
    Explanations

    phrases related to prayer, lunch, disappointment, and warnings

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional distress and social injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artney
    -0.66
    kefeller
    -0.66
    DonaldTrump
    -0.64
     Moroc
    -0.63
     referen
    -0.62
     mosqu
    -0.61
    chnology
    -0.61
     incorpor
    -0.61
    soDeliveryDate
    -0.60
    eday
    -0.59
    POSITIVE LOGITS
    Semitism
    0.58
     PTSD
    0.57
    xit
    0.56
    ctive
    0.56
    votes
    0.56
     Penalty
    0.54
     captcha
    0.53
     bias
    0.53
    ulence
    0.53
     inflic
    0.50
    Activations Density 1.668%

    No Known Activations