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. 18127
    Prev
    Next
    INDEX
    Explanations

    information related to companies and events that could affect them

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" used to indicate existence or state of being across various contexts

    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
    âĶ
    -0.69
    Newsletter
    -0.67
     âĶľâĶĢâĶĢ
    -0.65
     Mechanical
    -0.62
     beforehand
    -0.61
    cit
    -0.61
    ãĢĤ
    -0.61
    */
    -0.60
    ":[{"
    -0.58
    omever
    -0.57
    POSITIVE LOGITS
     suing
    1.17
     gearing
    1.09
     poised
    1.07
     reeling
    1.00
     launching
    0.96
     recalling
    0.96
     apologizing
    0.96
     shutting
    0.93
     eyeing
    0.93
     preparing
    0.91
    Activations Density 0.192%

    No Known Activations