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. 10-RES-JB
    6. 13508
    Prev
    Next
    INDEX
    Explanations

    references to political or social reforms

    oai_token-act-pair · gpt-3.5-turbo

    references to reform-related topics or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gaard
    -0.65
     infer
    -0.62
     McA
    -0.61
    ordon
    -0.61
     Saud
    -0.60
    ammy
    -0.60
    DoS
    -0.59
     Bryant
    -0.59
     Coulter
    -0.59
     Starg
    -0.58
    POSITIVE LOGITS
    ulation
    1.19
    atories
    1.17
    atted
    1.16
    ers
    1.16
    ulated
    1.16
    ulatory
    1.11
    ulations
    1.11
    er
    1.04
    rats
    1.01
    ulating
    0.96
    Activations Density 0.041%

    No Known Activations