© 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. 0-RES-JB
    11. 1477
    Prev
    Next
    INDEX
    Explanations

    invitations or calls to action

    oai_token-act-pair · gpt-3.5-turbo

    words related to invitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mills
    -0.72
     recovered
    -0.71
    Sym
    -0.65
     Measures
    -0.64
     Cutter
    -0.63
    src
    -0.62
     Stafford
    -0.61
     Tuc
    -0.61
     totality
    -0.60
    DER
    -0.59
    POSITIVE LOGITS
     invite
    3.86
     invites
    2.71
     invitation
    2.59
     invitations
    2.27
     inviting
    1.93
     invited
    1.91
    inv
    1.38
     welcome
    1.32
     encourage
    1.21
    Inv
    1.15
    Activations Density 0.014%

    No Known Activations