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. 2603
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals, institutions, and places

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals, institutions, or literary works

    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
    together
    -0.86
    comings
    -0.83
    jen
    -0.82
    ngth
    -0.81
    AMY
    -0.80
    ERG
    -0.79
    rez
    -0.79
    actionDate
    -0.79
    hold
    -0.73
    tle
    -0.71
    POSITIVE LOGITS
    uyomi
    0.83
     Revival
    0.77
     Massacre
    0.76
     Society
    0.76
     Foundation
    0.71
     fame
    0.69
     Syndicate
    0.69
     9000
    0.66
     Festival
    0.66
     imitation
    0.65
    Activations Density 0.264%

    No Known Activations