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. 21623
    Prev
    Next
    INDEX
    Explanations

    locations or geographical features

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" and its variations in context

    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
    wcsstore
    -0.71
     flashback
    -0.68
    rix
    -0.68
    Mom
    -0.68
     expr
    -0.68
    ventus
    -0.66
    pkg
    -0.66
    thood
    -0.65
    ality
    -0.65
    pelling
    -0.64
    POSITIVE LOGITS
     continent
    1.34
     coastline
    1.27
     peninsula
    1.25
     coasts
    1.25
     outskirts
    1.24
     shores
    1.19
     northern
    1.19
     island
    1.16
     coast
    1.16
     northeastern
    1.14
    Activations Density 0.358%

    No Known Activations