© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12538
    Prev
    Next
    INDEX
    Explanations

    announcements or official statements within a written text

    oai_token-act-pair · gpt-3.5-turbo

    key terms associated with announcements, actions, and documentation in formal contexts

    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
    ĪĴ
    -0.71
     srf
    -0.69
    ao
    -0.66
    afer
    -0.60
    ãĤ«
    -0.60
     appet
    -0.56
    Bee
    -0.55
    imble
    -0.54
    agog
    -0.53
    Weather
    -0.51
    POSITIVE LOGITS
     anew
    1.03
     herself
    0.88
     myself
    0.88
     anonymously
    0.87
     himself
    0.87
     aloud
    0.82
     manually
    0.81
     yourself
    0.78
     anyway
    0.77
     ourselves
    0.76
    Activations Density 0.373%

    No Known Activations