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. 12-RES-JB
    6. 7004
    Prev
    Next
    INDEX
    Explanations

    words related to leadership, progress, and success

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the word "head" in various contexts and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parenthood
    -0.64
     autos
    -0.63
     Nightmares
    -0.63
     Mub
    -0.59
     Mellon
    -0.56
     Brotherhood
    -0.55
     Chocobo
    -0.55
     Niet
    -0.54
    illation
    -0.54
     Gandhi
    -0.53
    POSITIVE LOGITS
    canon
    1.09
    lining
    1.08
    shots
    1.04
    space
    1.04
    liners
    1.03
    count
    1.03
    quarter
    1.02
    strong
    1.01
    hun
    1.00
    gear
    0.99
    Activations Density 0.027%

    No Known Activations