© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23875
    Prev
    Next
    INDEX
    Explanations

    references to the validity of something, such as email addresses, tickets, opinions, contracts, and IDs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "valid" in various contexts

    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
    ILA
    -0.80
     Sisters
    -0.75
    hedon
    -0.74
    Mania
    -0.67
    hedral
    -0.66
    hani
    -0.64
    cipl
    -0.63
    HI
    -0.62
    azel
    -0.62
    OPS
    -0.61
    POSITIVE LOGITS
    ating
    0.97
     valid
    0.93
    ations
    0.84
    iated
    0.84
    ators
    0.83
    ifiable
    0.79
    ational
    0.79
    itimate
    0.78
    iation
    0.78
    ifying
    0.76
    Activations Density 0.004%

    No Known Activations