© 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. 7-RES-JB
    11. 8644
    Prev
    Next
    INDEX
    Explanations

    verbs related to announcements or hints towards future events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to announcements and hints about future events or releases

    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
    tein
    -0.80
    istries
    -0.74
    isol
    -0.70
    ptic
    -0.70
    erning
    -0.67
    bara
    -0.66
    oard
    -0.66
    rosse
    -0.63
    itar
    -0.62
    column
    -0.62
    POSITIVE LOGITS
    soDeliveryDate
    0.79
     Parenthood
    0.76
     TBA
    0.72
    uled
    0.71
     beforehand
    0.68
     TBD
    0.65
     by
    0.65
     UD
    0.64
     contempor
    0.62
    Crash
    0.61
    Activations Density 0.097%

    No Known Activations