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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 19695
    Prev
    Next
    INDEX
    Explanations

    instances where the text discusses technology advancement and innovation

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" and its usage in various contexts

    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
    imon
    -0.66
     Rusty
    -0.66
     âĺħ
    -0.66
     unfocusedRange
    -0.64
     Bearing
    -0.63
     è£ıè
    -0.63
     Dres
    -0.63
    ongh
    -0.62
    dden
    -0.62
     Amin
    -0.61
    POSITIVE LOGITS
    'd
    0.93
     intended
    0.91
     saw
    0.88
     wished
    0.85
    've
    0.84
    're
    0.83
     desired
    0.81
     chanted
    0.81
     lawfully
    0.81
     transitioned
    0.80
    Activations Density 0.563%

    No Known Activations