© 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. 9075
    Prev
    Next
    INDEX
    Explanations

    references to a specific location, Fort Detrick

    oai_token-act-pair · gpt-3.5-turbo

    references to 'Fort' locations or facilities

    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
    lihood
    -0.63
     eclipse
    -0.59
     antitrust
    -0.58
    Companies
    -0.58
    Publisher
    -0.57
    ucl
    -0.57
     OECD
    -0.57
    lyak
    -0.57
    Accessory
    -0.56
    clips
    -0.56
    POSITIVE LOGITS
    uitous
    1.41
    itude
    1.21
     Lauderdale
    1.15
    ieth
    1.12
    dinand
    1.06
    resses
    1.01
    itud
    0.96
    itudes
    0.91
    folios
    0.89
    oise
    0.89
    Activations Density 0.027%

    No Known Activations