© 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. 11-RES-JB
    11. 23744
    Prev
    Next
    INDEX
    Explanations

    references to the city of Portland

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Portland and its associated 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
    maid
    -0.88
    hare
    -0.78
     Typhoon
    -0.69
     reckon
    -0.67
    bler
    -0.67
    bomb
    -0.66
    kh
    -0.65
    pter
    -0.65
    bourg
    -0.64
    irsch
    -0.63
    POSITIVE LOGITS
     Timbers
    1.36
     Oregon
    1.02
     Trail
    0.99
    ia
    0.97
    Oregon
    0.92
     Ducks
    0.89
    icut
    0.89
    ians
    0.86
    ION
    0.85
    sylvania
    0.83
    Activations Density 0.062%

    No Known Activations