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. 12-RES-JB
    6. 15072
    Prev
    Next
    INDEX
    Explanations

    statements about opinions, beliefs, or evaluations

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

    statements reflecting people's perceptions or beliefs about themselves and their circumstances

    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
    ornia
    -0.84
    nesday
    -0.77
    bernatorial
    -0.74
    isance
    -0.74
    hess
    -0.73
    berus
    -0.72
    ospons
    -0.70
    uitous
    -0.69
    icago
    -0.68
    alion
    -0.67
    POSITIVE LOGITS
     conditioned
    1.11
     fascinated
    1.09
     unaware
    1.08
     ignorant
    1.04
     accustomed
    1.04
     attracted
    1.03
     misled
    1.03
     unconsciously
    1.02
     diseng
    1.02
     swayed
    1.01
    Activations Density 0.291%

    No Known Activations