© 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. 2-RES-JB
    11. 4054
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a cause-and-effect relationship

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "When" indicating conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agin
    -0.69
    harm
    -0.69
    number
    -0.62
    alle
    -0.61
    atic
    -0.61
    ach
    -0.59
    ymph
    -0.58
    rolet
    -0.57
    nut
    -0.56
    Jew
    -0.56
    POSITIVE LOGITS
    soever
    1.34
    irlf
    0.91
     asked
    0.83
     confronted
    0.81
    bestos
    0.79
    phalt
    0.78
    quickShipAvailable
    0.77
    entimes
    0.77
    ĪĴ
    0.75
    itialized
    0.72
    Activations Density 0.046%

    No Known Activations