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. 20348
    Prev
    Next
    INDEX
    Explanations

    words related to being surrounded or surroundedness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "surrounded."

    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
    uh
    -0.68
    eway
    -0.66
    hist
    -0.64
    der
    -0.64
     wee
    -0.64
    err
    -0.63
    odor
    -0.63
    bal
    -0.62
    oi
    -0.62
     nerv
    -0.62
    POSITIVE LOGITS
     surrounded
    0.93
     surround
    0.89
    htaking
    0.87
     surrounds
    0.80
    bys
    0.80
    ength
    0.76
    angelo
    0.73
    ouver
    0.72
    ecause
    0.71
    ournal
    0.70
    Activations Density 0.016%

    No Known Activations