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. 11-RES-JB
    6. 10726
    Prev
    Next
    INDEX
    Explanations

    organizations and specific entities, potentially relating to disputes or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or entities, particularly in a political or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     Unloaded
    -0.72
    reviewed
    -0.66
    amia
    -0.65
    cedented
    -0.65
    NetMessage
    -0.64
    xtap
    -0.62
    ulia
    -0.62
    akens
    -0.61
    ãĥ´
    -0.61
    effective
    -0.61
    POSITIVE LOGITS
     staffer
    1.22
     thugs
    1.19
     waitress
    1.13
     bartender
    1.12
     clerk
    1.09
     reporter
    1.08
     interviewer
    1.07
     crew
    1.07
     supervisor
    1.05
     dispatcher
    1.04
    Activations Density 0.506%

    No Known Activations