© 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. 0-RES-JB
    11. 16418
    Prev
    Next
    INDEX
    Explanations

    words related to sensors and regulators

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chic
    -0.67
     Hatt
    -0.67
     Holl
    -0.66
     ess
    -0.66
     Mons
    -0.63
     XP
    -0.62
     Camp
    -0.62
     necessities
    -0.61
    naires
    -0.61
    hom
    -0.60
    POSITIVE LOGITS
    ensor
    3.43
    icer
    2.59
     Institutes
    1.27
     censor
    1.23
    leeve
    1.16
     regulator
    1.15
    ÄŁ
    1.14
    instein
    1.12
    heastern
    1.08
    ocker
    1.00
    Activations Density 0.040%

    No Known Activations