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. 10-RES-JB
    6. 1804
    Prev
    Next
    INDEX
    Explanations

    words related to locations and geographic entities

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms related to places, people, and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pedia
    -0.59
    è¦ļéĨĴ
    -0.55
    pmwiki
    -0.55
    oidal
    -0.51
    minster
    -0.49
    ãĤ¨ãĥ«
    -0.48
    racuse
    -0.47
    soft
    -0.47
     unfocusedRange
    -0.46
    AGES
    -0.45
    POSITIVE LOGITS
    there
    0.55
     thereof
    0.50
    charg
    0.46
    aura
    0.45
    have
    0.45
    ah
    0.44
    arming
    0.44
    both
    0.43
    husband
    0.43
    aries
    0.42
    Activations Density 0.405%

    No Known Activations