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. 17756
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express conditionality or actions performed 'with the intention of'

    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
    olved
    -0.60
     Accessed
    -0.57
    Lens
    -0.56
    iday
    -0.54
    izoph
    -0.54
    TPPStreamerBot
    -0.53
    ool
    -0.52
    irlf
    -0.52
    ICO
    -0.52
    asus
    -0.51
    POSITIVE LOGITS
     not
    1.31
    not
    1.13
     NOT
    1.09
     to
    1.00
     never
    0.92
     NEVER
    0.90
    never
    0.84
    Not
    0.81
    vity
    0.79
     Not
    0.78
    Activations Density 0.199%

    No Known Activations