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. 11905
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases ending in a full stop

    oai_token-act-pair · gpt-3.5-turbo

    periods, indicating the end of statements or thoughts

    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
     carbohyd
    -0.91
     teasp
    -0.90
     volunte
    -0.87
    yip
    -0.86
     subur
    -0.86
     pione
    -0.83
    escription
    -0.83
    »Ĵ
    -0.82
    apeshifter
    -0.81
     tremend
    -0.80
    POSITIVE LOGITS
     Firstly
    1.74
     Especially
    1.65
     Certainly
    1.64
     Particularly
    1.51
     Perhaps
    1.39
     Suppose
    1.38
     Surely
    1.38
    Firstly
    1.32
     Regardless
    1.31
     Personally
    1.31
    Activations Density 0.454%

    No Known Activations