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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6403
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and government actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal and governmental issues

    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
    eday
    -0.62
    advert
    -0.57
    ãĥĩãĤ£
    -0.56
    Untitled
    -0.55
     pim
    -0.52
    NER
    -0.50
    erenn
    -0.50
     notor
    -0.50
    retty
    -0.50
     defin
    -0.50
    POSITIVE LOGITS
     Belfast
    0.75
     amid
    0.69
     Rohingya
    0.68
    ¶
    0.65
    .--
    0.62
     Replay
    0.61
    âĢİ
    0.59
    "},
    0.59
     Copyright
    0.57
     Regarding
    0.56
    Activations Density 0.897%

    No Known Activations