© 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. 4-RES-JB
    11. 407
    Prev
    Next
    INDEX
    Explanations

    words related to subscribing to newsletters or services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription actions

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

    No Comments

    Negative Logits
    bra
    -0.80
    ball
    -0.77
     Morg
    -0.75
     Dull
    -0.73
    stood
    -0.69
    footed
    -0.67
    pex
    -0.65
    ilde
    -0.65
    pel
    -0.65
     Pens
    -0.65
    POSITIVE LOGITS
     subscriptions
    0.99
     subscribing
    0.94
     subscribe
    0.88
    Interstitial
    0.87
    interstitial
    0.83
     subscription
    0.81
     binge
    0.81
    ickets
    0.81
     privileges
    0.79
    iatus
    0.79
    Activations Density 0.007%

    No Known Activations