© 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. 11-RES-JB
    6. 5026
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical actions

    oai_token-act-pair · gpt-3.5-turbo

    actions involving personal expression and transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugu
    -0.68
    yah
    -0.66
    )</
    -0.64
    advertising
    -0.61
    ranch
    -0.57
    They
    -0.56
    Introduced
    -0.56
    We
    -0.55
    hedon
    -0.55
    You
    -0.55
    POSITIVE LOGITS
     my
    2.37
     myself
    2.22
     MY
    1.58
     mine
    1.46
     My
    1.39
    My
    1.38
    my
    1.38
     me
    1.05
    MY
    0.91
     I
    0.90
    Activations Density 1.025%

    No Known Activations