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. 16938
    Prev
    Next
    INDEX
    Explanations

    personal statements starting with "If I"

    oai_token-act-pair · gpt-3.5-turbo

    personal statements and expressions of desire or intention

    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
    MpServer
    -0.78
    interstitial
    -0.69
    Ô
    -0.69
    Reviewer
    -0.63
    catentry
    -0.63
    Sharp
    -0.63
    SourceFile
    -0.59
    Flor
    -0.59
    Magikarp
    -0.59
    BAT
    -0.58
    POSITIVE LOGITS
     hadn
    1.10
     weren
    1.07
     were
    1.00
     wanted
    0.94
     want
    0.90
    're
    0.87
     ever
    0.87
     cared
    0.86
    were
    0.86
     wanna
    0.85
    Activations Density 0.119%

    No Known Activations