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. 10202
    Prev
    Next
    INDEX
    Explanations

    words containing the subsequence "iar"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or characters

    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
    ester
    -0.77
    aic
    -0.71
     Santos
    -0.65
    anwhile
    -0.63
    oak
    -0.62
    hend
    -0.62
     Startup
    -0.62
     Machina
    -0.61
     Vend
    -0.60
    hetamine
    -0.59
    POSITIVE LOGITS
    ror
    1.06
    osc
    0.83
    ibrary
    0.79
    æ©
    0.78
    bis
    0.77
    aries
    0.75
    arial
    0.75
    andom
    0.74
    ates
    0.73
    respective
    0.72
    Activations Density 0.028%

    No Known Activations