© 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. 8-RES-JB
    11. 3207
    Prev
    Next
    INDEX
    Explanations

    phrases related to upcoming events or activities

    oai_token-act-pair · gpt-3.5-turbo

    future intentions or planned events

    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
    76561
    -0.81
    ukemia
    -0.69
    JD
    -0.66
    ourke
    -0.66
    Mom
    -0.64
    Weak
    -0.64
    quickShipAvailable
    -0.63
     misunderstanding
    -0.62
     Syndrome
    -0.61
    rary
    -0.60
    POSITIVE LOGITS
     be
    1.18
     continue
    1.14
     unveil
    1.05
     undoubtedly
    0.98
     doubtless
    0.98
     begin
    0.96
     introduce
    0.94
     arrive
    0.94
     remain
    0.93
     announce
    0.93
    Activations Density 0.210%

    No Known Activations