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. 8-RES-JB
    6. 17395
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that end in a full stop

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vind
    -0.72
    opian
    -0.71
     ogre
    -0.70
    emort
    -0.70
     madness
    -0.70
     maniac
    -0.69
    quer
    -0.69
     beast
    -0.69
    itri
    -0.67
    allah
    -0.67
    POSITIVE LOGITS
     Whereas
    1.28
     According
    1.26
     Earlier
    1.22
     Though
    1.13
     While
    1.12
     Firstly
    1.10
     Although
    1.07
     Aside
    1.06
     Instead
    1.05
     Already
    1.04
    Activations Density 0.447%

    No Known Activations