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. 3-RES-JB
    6. 21827
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific organizations, locations, and individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names, particularly those related to institutions, events, and notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.46
    SN
    -0.44
    PATH
    -0.44
    rawdownloadcloneembedreportprint
    -0.43
    Reviewer
    -0.43
    GMT
    -0.43
    href
    -0.43
    hillary
    -0.40
    NAS
    -0.40
    YN
    -0.40
    POSITIVE LOGITS
    eers
    0.56
     fame
    0.50
     fiasco
    0.49
    ioxide
    0.46
     imitation
    0.46
    culosis
    0.45
    arettes
    0.45
    enko
    0.45
    plete
    0.42
     syndrome
    0.41
    Activations Density 1.685%

    No Known Activations