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. 22719
    Prev
    Next
    INDEX
    Explanations

    words related to political or social change and improvement

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of reform

    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
     Frie
    -0.65
    DoS
    -0.64
     Ops
    -0.61
     Saud
    -0.60
    gaard
    -0.59
     Bryant
    -0.58
     TOTAL
    -0.58
     infer
    -0.58
     Coulter
    -0.57
    ordon
    -0.57
    POSITIVE LOGITS
    ulation
    1.26
    atted
    1.26
    ulated
    1.24
    ulations
    1.13
    ers
    1.12
    ulatory
    1.12
    atories
    1.10
    ulating
    1.02
    er
    0.97
    ulators
    0.94
    Activations Density 0.042%

    No Known Activations