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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22058
    Prev
    Next
    INDEX
    Explanations

    the word "realize" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "realize" and its variations to detect moments of awareness or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.83
    picking
    -0.70
     clipboard
    -0.69
     wrists
    -0.68
    oil
    -0.66
    reen
    -0.64
    cgi
    -0.63
     helmets
    -0.63
    ciating
    -0.62
    conservancy
    -0.62
    POSITIVE LOGITS
    ledged
    0.86
     realise
    0.83
     realize
    0.80
    REAM
    0.80
    âĶģ
    0.77
    ISION
    0.76
    urities
    0.75
     realizes
    0.75
    actly
    0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.75
    Activations Density 0.032%

    No Known Activations