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. 2-RES-JB
    6. 8576
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Sussex"

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and geographic features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieu
    -0.78
    brance
    -0.74
    wich
    -0.71
    orrow
    -0.71
    ebus
    -0.70
     skelet
    -0.69
    advertising
    -0.69
    stanbul
    -0.68
    gren
    -0.68
    estyles
    -0.68
    POSITIVE LOGITS
    rocal
    0.70
    cipl
    0.68
    armac
    0.68
     Draco
    0.63
     Malfoy
    0.63
    emale
    0.62
     Extension
    0.61
    cellence
    0.60
     ãĤµ
    0.60
     STATS
    0.60
    Activations Density 0.048%

    No Known Activations