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. 3-RES-JB
    6. 19973
    Prev
    Next
    INDEX
    Explanations

    phrases related to work or tasks being done

    oai_token-act-pair · gpt-3.5-turbo

    frequency and repetition of commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ety
    -0.63
    eport
    -0.61
    itialized
    -0.57
    ¬¼
    -0.55
    iban
    -0.51
    ©¶æ
    -0.49
    itis
    -0.49
    ishly
    -0.48
    vest
    -0.48
    rack
    -0.48
    POSITIVE LOGITS
     albeit
    0.83
     namely
    0.82
     although
    0.71
     whereas
    0.71
     including
    0.69
     regardless
    0.65
     which
    0.64
    SPONSORED
    0.62
     thereby
    0.61
     aka
    0.60
    Activations Density 0.983%

    No Known Activations