Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10331
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize similarity or consistency

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "the same" or variations of it related to similarity

    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
     amongst
    -0.71
    wana
    -0.69
    oa
    -0.68
     among
    -0.67
     Leilan
    -0.58
    gew
    -0.58
    abin
    -0.57
    mund
    -0.56
    Soul
    -0.56
    isma
    -0.56
    POSITIVE LOGITS
     same
    2.73
    same
    2.45
     Same
    2.03
    Same
    1.87
     opposite
    1.70
     exact
    1.55
     identical
    1.25
     inverse
    1.09
     reverse
    1.05
    ses
    1.04
    Activations Density 0.301%

    No Known Activations