© 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. 7-RES-JB
    11. 24557
    Prev
    Next
    INDEX
    Explanations

    names of individuals or places, particularly with a strong emphasis on Ar

    oai_token-act-pair · gpt-3.5-turbo

    words and terms related to the theme of "disaster" or "emergency."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.67
    fml
    -0.62
    ACTED
    -0.61
    äºĶ
    -0.60
    ĸļ
    -0.60
    ONSORED
    -0.59
    ĺħ
    -0.58
    ²¾
    -0.58
    è¦ļéĨĴ
    -0.56
    IZE
    -0.56
    POSITIVE LOGITS
    haus
    0.82
    alk
    0.75
    hof
    0.75
    arios
    0.71
    ollen
    0.69
    gard
    0.68
    alla
    0.67
    iland
    0.66
    lov
    0.66
    olini
    0.65
    Activations Density 0.143%

    No Known Activations