© 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. 17600
    Prev
    Next
    INDEX
    Explanations

    phrases related to observation or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "look" in various contexts

    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
    icipated
    -0.67
    shown
    -0.64
    mentioned
    -0.63
    RT
    -0.61
    kson
    -0.59
    olor
    -0.59
     collaps
    -0.57
    ille
    -0.57
    mt
    -0.56
    Published
    -0.55
    POSITIVE LOGITS
     inward
    0.91
     elsewhere
    0.89
     favorably
    0.83
     foolish
    0.81
     abroad
    0.81
     kindly
    0.76
     forward
    0.75
     backward
    0.74
     beyond
    0.74
     Forward
    0.74
    Activations Density 0.046%

    No Known Activations