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. 2315
    Prev
    Next
    INDEX
    Explanations

    specific references to conferences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of conferences

    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
    ter
    -0.70
    kowski
    -0.70
    cher
    -0.67
    aft
    -0.65
    laus
    -0.65
    gettable
    -0.64
    DonaldTrump
    -0.63
    =#
    -0.62
    iless
    -0.62
     recoil
    -0.61
    POSITIVE LOGITS
     conference
    0.86
     conferences
    0.84
    ference
    0.80
    eers
    0.80
    erences
    0.75
     meetings
    0.75
     attendees
    0.75
     organisers
    0.74
    ivals
    0.74
     presentations
    0.74
    Activations Density 0.020%

    No Known Activations