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. 9-RES-JB
    6. 6195
    Prev
    Next
    INDEX
    Explanations

    phrases related to invisibility or being hidden

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to invisibility or things that are hidden from the general public

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uesday
    -0.60
    FTWARE
    -0.60
     hangs
    -0.59
    atto
    -0.59
    rice
    -0.58
    ornia
    -0.58
     themed
    -0.58
    Krist
    -0.57
    BACK
    -0.56
    KA
    -0.55
    POSITIVE LOGITS
     mortals
    1.20
     outsiders
    1.12
     passers
    1.00
     onlook
    0.98
     anyone
    0.95
     anybody
    0.92
     humans
    0.92
     civilized
    0.91
     humankind
    0.91
     mainstream
    0.89
    Activations Density 0.380%

    No Known Activations