Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18914
    Prev
    Next
    INDEX
    Explanations

    phrases where the speaker expresses personal preferences or experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing strong personal preferences or fandom

    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
    eworks
    -0.80
    bars
    -0.71
    querade
    -0.69
     omin
    -0.69
     alternatives
    -0.67
    rooms
    -0.67
    iths
    -0.66
     arrangements
    -0.66
    elight
    -0.66
    mates
    -0.65
    POSITIVE LOGITS
     believer
    1.39
     sucker
    1.28
     proponent
    1.20
     fan
    1.20
     subscriber
    1.04
     programmer
    1.03
     skept
    1.02
     follower
    1.01
     lover
    1.00
     gamer
    0.99
    Activations Density 0.107%

    No Known Activations