© 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. 2-RES-JB
    11. 23568
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement instruments, particularly those ending in '-ometer'

    oai_token-act-pair · gpt-3.5-turbo

    words related to measurement and instrumentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    giving
    -0.81
    gotten
    -0.72
    represented
    -0.72
    edu
    -0.71
    ggies
    -0.70
    lez
    -0.70
    lar
    -0.66
    eve
    -0.66
    eworld
    -0.66
    sle
    -0.64
    POSITIVE LOGITS
    ometer
    1.14
    ometers
    0.99
    ograph
    0.82
    ographer
    0.78
    apter
    0.77
     measuring
    0.77
    Sensor
    0.73
     dipping
    0.69
     gauge
    0.69
     calibration
    0.67
    Activations Density 0.016%

    No Known Activations