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. 5-RES-JB
    6. 5099
    Prev
    Next
    INDEX
    Explanations

    mentions of email newsletters or bulletins

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the acronym "ES" across multiple contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estate
    -0.79
    ichick
    -0.75
    olulu
    -0.73
    zzle
    -0.72
    ãĥĥãĥĪ
    -0.72
    assad
    -0.72
    staff
    -0.69
    iance
    -0.69
    zers
    -0.69
    allery
    -0.67
    POSITIVE LOGITS
    TERN
    1.29
    IGH
    1.05
    TRY
    1.04
    ET
    1.04
    CENT
    1.02
    SAY
    1.02
    IDES
    1.00
    SE
    0.99
    GO
    0.99
    FIN
    0.99
    Activations Density 0.016%

    No Known Activations