Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 2305
    Prev
    Next
    INDEX
    Explanations

    the name "Kar" along with different suffixes or prefixes attached to it

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kar" and its variations throughout the text

    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
    IBLE
    -0.97
    byter
    -0.79
    FORMATION
    -0.76
    CRIP
    -0.76
    ibilities
    -0.76
    CAST
    -0.75
    ĨĴ
    -0.72
    LECT
    -0.70
     Unic
    -0.70
    terday
    -0.70
    POSITIVE LOGITS
    thal
    1.10
    zai
    1.01
    istani
    0.97
    amaz
    0.97
    acan
    0.93
    ratom
    0.93
    sten
    0.89
    won
    0.89
    agame
    0.87
    oled
    0.85
    Activations Density 0.010%

    No Known Activations