© 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. 8-RES-JB
    11. 18575
    Prev
    Next
    INDEX
    Explanations

    email-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to news alerts and emails

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fig
    -0.75
    flies
    -0.75
    fulness
    -0.70
    itive
    -0.64
    wo
    -0.64
    figured
    -0.64
    ivism
    -0.63
    steen
    -0.62
    blind
    -0.62
    stood
    -0.60
    POSITIVE LOGITS
     Emails
    0.85
    VERTISEMENT
    0.78
    ļéĨĴ
    0.74
     Transcript
    0.74
     transcript
    0.72
     transcripts
    0.66
     Timeline
    0.66
     LAT
    0.65
     arming
    0.63
    etheless
    0.61
    Activations Density 0.022%

    No Known Activations