© 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. 0-RES-JB
    11. 16885
    Prev
    Next
    INDEX
    Explanations

    verbs expressing the act of creation or establishment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "created."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ory
    -0.63
    Rush
    -0.61
    smoking
    -0.60
     Fare
    -0.59
     Smoking
    -0.59
    tle
    -0.59
    Sem
    -0.58
    inence
    -0.58
     Hardy
    -0.57
    abouts
    -0.56
    POSITIVE LOGITS
     created
    3.30
    created
    2.49
     Created
    2.34
    Created
    2.09
     generated
    1.93
     invented
    1.78
     creation
    1.73
     formed
    1.73
     devised
    1.72
     spawned
    1.71
    Activations Density 0.019%

    No Known Activations