© 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. 4-RES-JB
    11. 10858
    Prev
    Next
    INDEX
    Explanations

    mentions of different hotels or inns, possibly focusing on specific names like "Gatlinburg Inn."

    oai_token-act-pair · gpt-3.5-turbo

    references to inns or lodging establishments

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

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.75
     litter
    -0.73
    vich
    -0.73
    xual
    -0.68
    izoph
    -0.68
     Stafford
    -0.65
    theless
    -0.64
    uyomi
    -0.64
    llor
    -0.61
    ¥
    -0.61
    POSITIVE LOGITS
    umerable
    1.24
    keeper
    1.15
    ocent
    0.98
    itial
    0.97
    isf
    0.94
     Inn
    0.92
    oc
    0.92
    keepers
    0.91
    ovo
    0.87
    okin
    0.87
    Activations Density 0.010%

    No Known Activations