© 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. 9-RES-JB
    11. 18406
    Prev
    Next
    INDEX
    Explanations

    instances where something is expected or anticipated

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to expectations and anticipations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azeera
    -0.65
    ovember
    -0.64
    arget
    -0.63
    hes
    -0.61
    utterstock
    -0.61
    anga
    -0.61
    itaire
    -0.61
    aware
    -0.60
    adder
    -0.58
    roit
    -0.58
    POSITIVE LOGITS
     payoff
    0.78
     outcome
    0.75
     Paradise
    0.71
     arrival
    0.70
    soon
    0.69
     imminent
    0.67
     turnout
    0.66
     foreseeable
    0.65
     tomorrow
    0.65
    pour
    0.64
    Activations Density 0.253%

    No Known Activations