© 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. 2432
    Prev
    Next
    INDEX
    Explanations

    past events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to consequences or outcomes of actions or events

    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
    azel
    -0.71
    ciating
    -0.71
    quire
    -0.70
    etz
    -0.69
    enne
    -0.68
    76561
    -0.68
    amines
    -0.67
    ryu
    -0.66
    atography
    -0.66
    20439
    -0.66
    POSITIVE LOGITS
     tragically
    1.28
     malfunction
    1.20
     vanished
    1.20
     crumbling
    1.16
     mysteriously
    1.16
     collapsed
    1.15
     abruptly
    1.14
     undone
    1.13
     disinteg
    1.12
     collapse
    1.12
    Activations Density 0.994%

    No Known Activations