Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15848
    Prev
    Next
    INDEX
    Explanations

    references to the state of Ohio in the context of various subjects and contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Ohio and its related entities

    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
    ding
    -0.92
    Austral
    -0.77
    grading
    -0.71
     Imran
    -0.69
    rey
    -0.66
    wards
    -0.66
    eways
    -0.65
    ded
    -0.65
    dk
    -0.64
     Cheong
    -0.64
    POSITIVE LOGITS
     Ohio
    0.95
     Buc
    0.89
    Ohio
    0.86
     Dispatch
    0.81
     Akron
    0.80
     State
    0.80
     OH
    0.76
     Cavaliers
    0.76
     Valley
    0.75
    ans
    0.72
    Activations Density 0.053%

    No Known Activations