© 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. 3-RES-JB
    11. 3102
    Prev
    Next
    INDEX
    Explanations

    words related to verification and validation processes, such as "validation", "disclosure", "verification", and "activation"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to validation and verification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ells
    -0.75
    eva
    -0.75
    tiny
    -0.75
    semble
    -0.72
    resp
    -0.69
    inal
    -0.69
    uate
    -0.69
    enced
    -0.68
    otrop
    -0.67
     Clancy
    -0.67
    POSITIVE LOGITS
     lapse
    0.85
    eering
    0.81
     mechanism
    0.81
    anguage
    0.80
     avoidance
    0.80
     techniques
    0.79
     prevention
    0.79
    uyomi
    0.78
     process
    0.78
    ary
    0.78
    Activations Density 0.186%

    No Known Activations