© 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. 6989
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating the start of an action or process

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "begin" and "begun."

    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
    Bey
    -0.79
    pter
    -0.67
    inkle
    -0.66
    assic
    -0.66
    elo
    -0.64
    warts
    -0.63
    uras
    -0.63
     gods
    -0.63
    alted
    -0.61
    Dad
    -0.61
    POSITIVE LOGITS
     preparations
    1.02
     anew
    0.94
     rollout
    0.89
     preliminary
    0.89
     reorgan
    0.88
     dismantling
    0.86
     negotiations
    0.86
     renovations
    0.85
     experimenting
    0.85
     consultations
    0.85
    Activations Density 0.161%

    No Known Activations