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

    Neuronpedia

    APICircuit 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. 14788
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names of entities

    oai_token-act-pair · gpt-3.5-turbo

    recurring definite articles in a variety of contexts

    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
    earch
    -0.82
    TPPStreamerBot
    -0.74
    thood
    -0.71
    ����
    -0.69
    igne
    -0.68
    Boost
    -0.67
    NetMessage
    -0.66
    pai
    -0.65
    adle
    -0.62
    ovo
    -0.62
    POSITIVE LOGITS
    oret
    1.28
     implication
    1.28
     result
    1.25
     latter
    1.24
     gist
    1.24
     resultant
    1.13
     ensuing
    1.11
     resulting
    1.10
     reason
    1.07
     irony
    1.05
    Activations Density 0.329%

    No Known Activations