© 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. 1-RES-JB
    11. 24008
    Prev
    Next
    INDEX
    Explanations

    words related to validation processes or assessments

    oai_token-act-pair · gpt-3.5-turbo

    the concept of validation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    -0.82
    auld
    -0.74
    kers
    -0.74
    hunt
    -0.72
    thus
    -0.71
    eworld
    -0.69
    bors
    -0.68
    Ill
    -0.68
    affer
    -0.68
    ood
    -0.68
    POSITIVE LOGITS
     validation
    1.17
     validate
    1.05
     validated
    0.98
    idated
    0.84
    iably
    0.73
     legitim
    0.71
    rador
    0.70
    atable
    0.69
     confirmation
    0.69
     partName
    0.68
    Activations Density 0.012%

    No Known Activations