© 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. 1-RES-JB
    11. 24042
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizations or entities with the word "Found" in them

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Found" and related forms in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.84
    bid
    -0.69
     indign
    -0.67
    adish
    -0.65
    displayText
    -0.63
    step
    -0.63
    perature
    -0.61
     ABS
    -0.61
    smart
    -0.61
    shock
    -0.60
    POSITIVE LOGITS
    Found
    1.34
     Found
    1.08
    ãĤ¤ãĥĪ
    1.01
    indal
    0.84
    found
    0.80
    ãĤ¼
    0.79
    ãĤ¦ãĤ¹
    0.79
    -+-+
    0.78
    ãĥĭ
    0.77
    ational
    0.76
    Activations Density 0.008%

    No Known Activations