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. 4-RES-JB
    6. 8932
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Rit" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Pritchard" and its variations

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

    No Comments

    Negative Logits
    ©¶æ
    -0.90
    ¥ŀ
    -0.83
    ¶ħ
    -0.77
    ĨĴ
    -0.76
    «ĺ
    -0.71
    merce
    -0.65
    ¥µ
    -0.64
    ŃĶ
    -0.63
     instantaneous
    -0.63
    ĻĤ
    -0.62
    POSITIVE LOGITS
    ual
    0.96
    chard
    0.96
    chet
    0.91
    ravel
    0.89
    ique
    0.88
    tered
    0.86
    sis
    0.81
    ting
    0.81
    ters
    0.80
    sch
    0.79
    Activations Density 0.010%

    No Known Activations