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. 23885
    Prev
    Next
    INDEX
    Explanations

    names that start with 'R' followed by a surname starting with 'i'

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals and organizations in a specific context

    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
    ãĤ¶
    -0.75
    lehem
    -0.69
    \<
    -0.66
    natureconservancy
    -0.62
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
    nown
    -0.60
    ãĥ¼ãĤ¯
    -0.58
     adolesc
    -0.58
    »Ĵ
    -0.57
    apult
    -0.57
    POSITIVE LOGITS
    backer
    0.96
    ordan
    0.76
     CTR
    0.71
    kefeller
    0.68
    vous
    0.67
    restling
    0.66
     sshd
    0.65
    eyes
    0.65
    aiden
    0.64
     Grac
    0.64
    Activations Density 0.619%

    No Known Activations