© 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. 9-RES-JB
    11. 18068
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or organizations with the word "Mid" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Midland."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.83
     captcha
    -0.80
    76561
    -0.79
    çīĪ
    -0.72
    igslist
    -0.69
     clearance
    -0.65
    naires
    -0.63
    ained
    -0.62
     payable
    -0.60
    FTWARE
    -0.60
    POSITIVE LOGITS
    western
    0.97
    range
    0.95
    season
    0.88
    wives
    0.87
    winter
    0.87
    town
    0.86
    century
    0.86
    night
    0.84
    mers
    0.84
    court
    0.82
    Activations Density 0.022%

    No Known Activations