© 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. 2776
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or incidents involving specific locations

    oai_token-act-pair · gpt-3.5-turbo

    topics related to events or gatherings that may have societal implications

    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
    ocry
    -0.74
    notations
    -0.74
    -)
    -0.67
     recognise
    -0.64
     secondly
    -0.62
    oubted
    -0.61
     analyse
    -0.60
    qus
    -0.60
    relation
    -0.59
    âĢij
    -0.58
    POSITIVE LOGITS
     TODAY
    0.73
     embattled
    0.69
     Appalachian
    0.66
     NYPD
    0.64
     Hurricane
    0.64
     Harlem
    0.64
     homeless
    0.63
     Amtrak
    0.62
     Albuquerque
    0.62
     mayhem
    0.60
    Activations Density 1.853%

    No Known Activations