© 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. 966
    Prev
    Next
    INDEX
    Explanations

    the term "appointment"

    oai_token-act-pair · gpt-4-turbo

    phrases related to scheduling appointments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of appointments

    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
    sol
    -0.81
    Ïģ
    -0.80
    Ïī
    -0.76
    α
    -0.70
    mol
    -0.70
    κ
    -0.69
    jer
    -0.69
    VER
    -0.69
    patch
    -0.69
    DIV
    -0.68
    POSITIVE LOGITS
     appointments
    1.38
     appointment
    1.23
    ointment
    0.96
     fees
    0.87
    ointed
    0.86
     appoint
    0.83
    eering
    0.82
     visits
    0.81
     appointed
    0.75
     slots
    0.75
    Activations Density 0.010%

    No Known Activations