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. 4640
    Prev
    Next
    INDEX
    Explanations

    references to the character "Percival"

    oai_token-act-pair · gpt-3.5-turbo

    references to evaluations or ratings involving a hierarchical scoring system

    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
    built
    -0.74
    haar
    -0.68
    lessly
    -0.67
    omething
    -0.66
    sterdam
    -0.66
    print
    -0.66
    yout
    -0.65
    ividual
    -0.64
    prints
    -0.64
    mine
    -0.64
    POSITIVE LOGITS
    ival
    0.96
    iott
    0.80
    ves
    0.76
    ency
    0.73
    rous
    0.71
    uay
    0.69
    į
    0.68
    ption
    0.68
    ITIES
    0.66
    ipel
    0.65
    Activations Density 0.016%

    No Known Activations