© 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. 22476
    Prev
    Next
    INDEX
    Explanations

    references to specific measurements of distance, especially those related to miles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to distances and time measurements

    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
    NetMessage
    -0.70
    HCR
    -0.69
    SpaceEngineers
    -0.67
    EStreamFrame
    -0.65
    PsyNetMessage
    -0.64
     recruiting
    -0.62
    jri
    -0.61
    ettings
    -0.60
     solicitation
    -0.59
    ãĥ´ãĤ¡
    -0.59
    POSITIVE LOGITS
    glass
    1.10
    wise
    0.98
    ometers
    0.95
    cake
    0.92
    ometer
    0.88
    asus
    0.87
    ages
    0.87
    age
    0.85
    wheel
    0.83
    ature
    0.83
    Activations Density 0.102%

    No Known Activations