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. 11-RES-JB
    6. 19565
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entity "Skidmore College"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Skidmore College."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     writ
    -0.72
     sanity
    -0.66
     compounded
    -0.65
     starting
    -0.64
     sympt
    -0.64
     coupled
    -0.63
     stricken
    -0.63
     flu
    -0.61
     needless
    -0.59
     breeding
    -0.59
    POSITIVE LOGITS
    ysc
    1.44
    yrim
    1.31
    ipper
    1.24
    oln
    1.21
    ulpt
    1.21
    ril
    1.20
    illet
    1.19
    illed
    1.18
    ratch
    1.15
    irts
    1.13
    Activations Density 0.020%

    No Known Activations