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. 3890
    Prev
    Next
    INDEX
    Explanations

    references to locations or entities with 'Par' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Par," indicating a focus on places or organizations associated with that name

    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
     dwar
    -0.68
    sonian
    -0.65
    BILITIES
    -0.63
    éĹĺ
    -0.63
    CRIP
    -0.63
    士
    -0.62
    =]
    -0.61
    ħĭ
    -0.60
    OME
    -0.60
    !/
    -0.59
    POSITIVE LOGITS
    anoia
    1.34
    vati
    1.28
    agraph
    1.27
    rish
    1.19
    liament
    1.16
    alysis
    1.16
    allel
    1.14
    agon
    1.07
    iah
    1.07
    cel
    1.05
    Activations Density 0.012%

    No Known Activations