© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 17234
    Prev
    Next
    INDEX
    Explanations

    phrases related to government actions or policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the word "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stones
    -0.81
    ouls
    -0.81
    ocular
    -0.78
    TW
    -0.76
    kees
    -0.75
    nikov
    -0.74
     herself
    -0.72
    cient
    -0.72
    cients
    -0.72
    dan
    -0.71
    POSITIVE LOGITS
     retrieval
    1.30
     retention
    1.28
     disposal
    1.24
     reproduction
    1.24
     destruction
    1.23
     dissemination
    1.21
     evaluation
    1.13
     relocation
    1.12
     deletion
    1.12
     extermination
    1.12
    Activations Density 0.311%

    No Known Activations