© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 14718
    Prev
    Next
    INDEX
    Explanations

    the word "verify"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the process of verification

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

    No Comments

    Negative Logits
    NetMessage
    -0.83
    cent
    -0.71
    ovie
    -0.69
    theme
    -0.67
    tile
    -0.66
    wich
    -0.66
    Ëľ
    -0.66
     Sparrow
    -0.65
    court
    -0.65
    bid
    -0.65
    POSITIVE LOGITS
     verification
    1.01
     verify
    0.94
     verified
    0.91
     verifying
    0.82
     corrobor
    0.77
    ifies
    0.77
    ifying
    0.74
     authenticity
    0.74
     validity
    0.74
     guarant
    0.73
    Activations Density 0.027%

    No Known Activations