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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 17559
    Prev
    Next
    INDEX
    Explanations

    phrases related to updates or changes

    oai_token-act-pair · gpt-3.5-turbo

    references to updates and processes that involve changes or evaluations

    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
    aciously
    -0.68
     urgently
    -0.66
    azeera
    -0.64
    asus
    -0.63
    illions
    -0.63
    staking
    -0.63
     sacrific
    -0.62
     critically
    -0.61
    ModLoader
    -0.60
     challeng
    -0.59
    POSITIVE LOGITS
     except
    1.02
     until
    0.86
    .�
    0.83
    until
    0.83
     but
    0.77
    SPONSORED
    0.77
    .:
    0.77
    but
    0.76
     till
    0.74
     thereafter
    0.73
    Activations Density 0.697%

    No Known Activations