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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 666
    Prev
    Next
    INDEX
    Explanations

    anomalies or outliers in a series of text such as errors, formatting issues, or unnecessary symbols

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings or punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oun
    -0.88
     earthqu
    -0.85
    ¥ŀ
    -0.84
     satell
    -0.79
    ailability
    -0.75
     undermin
    -0.75
     metic
    -0.74
     ÂŃ
    -0.73
     tremend
    -0.72
     mathemat
    -0.72
    POSITIVE LOGITS
    )-
    1.55
    "-
    1.48
     -
    1.47
    -
    1.39
    -.
    1.38
    -(
    1.36
    :-
    1.35
    %-
    1.31
    -)
    1.27
    '-
    1.25
    Activations Density 0.117%

    No Known Activations