© 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. 3-RES-JB
    11. 15264
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "tad" at various strength levels

    oai_token-act-pair · gpt-3.5-turbo

    the word "tad" and its variations along with contextually related terms

    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
    naires
    -0.87
    icity
    -0.74
    iew
    -0.69
    naire
    -0.68
     subsequ
    -0.67
    oved
    -0.67
    pedia
    -0.65
    IDER
    -0.65
     lett
    -0.64
    eous
    -0.63
    POSITIVE LOGITS
    pole
    1.29
     tad
    0.94
    bit
    0.82
    DAY
    0.80
    wcsstore
    0.80
    metry
    0.79
    chery
    0.77
    rait
    0.75
    udos
    0.75
    jay
    0.74
    Activations Density 0.022%

    No Known Activations