© 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. 8-RES-JB
    6. 24047
    Prev
    Next
    INDEX
    Explanations

    words related to actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "do" and its variations in different contexts

    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
     Printed
    -0.69
     Ages
    -0.65
     Siren
    -0.63
    ORGE
    -0.63
    ITED
    -0.61
     Dise
    -0.60
    hog
    -0.58
    fields
    -0.56
    ary
    -0.55
     Madagascar
    -0.55
    POSITIVE LOGITS
    pez
    1.05
    oms
    0.98
    zed
    0.88
    actic
    0.86
    xx
    0.85
    omsday
    0.83
    ppel
    0.82
    ves
    0.80
     succeed
    0.80
     manage
    0.80
    Activations Density 0.072%

    No Known Activations