© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 17082
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication with the audience

    oai_token-act-pair · gpt-3.5-turbo

    first-person and collective pronouns

    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
    Accessory
    -0.69
    Newsletter
    -0.68
    ItemTracker
    -0.63
    nesota
    -0.63
    adic
    -0.63
    employment
    -0.61
    successful
    -0.60
    Shape
    -0.59
    rad
    -0.59
    Intern
    -0.59
    POSITIVE LOGITS
     apologize
    1.42
     apologise
    1.42
     apologies
    1.15
     urge
    1.13
     promise
    1.11
     hope
    1.11
     sincerely
    1.09
     recommend
    1.05
     assure
    1.04
     salute
    1.03
    Activations Density 0.249%

    No Known Activations