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. 10-RES-JB
    6. 13048
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Carm"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Carmelo" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FOIA
    -0.64
    uation
    -0.60
     Fargo
    -0.59
     odds
    -0.59
     payday
    -0.58
     mask
    -0.58
     Asgard
    -0.57
     Turks
    -0.56
     worth
    -0.56
     AMA
    -0.56
    POSITIVE LOGITS
    ichael
    1.46
    ageddon
    1.44
    aceutical
    1.24
    esan
    1.20
    elo
    1.10
    ovie
    1.10
    agna
    1.10
    essage
    1.06
    ountain
    1.02
    onica
    1.01
    Activations Density 0.040%

    No Known Activations