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. 6-RES-JB
    6. 8554
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with the word "This" and expressing a variety of thoughts or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¹ãĥĪ
    -1.01
    AZ
    -0.81
    ARS
    -0.80
    Ĭ±
    -0.78
    ivas
    -0.77
    Īè
    -0.77
    ©¶æ¥µ
    -0.77
    ãĤ¶
    -0.77
    aws
    -0.76
    ·
    -0.76
    POSITIVE LOGITS
     guy
    0.91
     week
    0.85
     kind
    0.83
     sort
    0.82
     century
    0.82
     morning
    0.82
     stuff
    0.77
     particular
    0.77
     secrecy
    0.76
     sucker
    0.76
    Activations Density 0.242%

    No Known Activations