© 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. 8-RES-JB
    11. 6073
    Prev
    Next
    INDEX
    Explanations

    phrases related to waiting or anticipating outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate anticipation or expectation about future 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
    quartered
    -0.70
    escent
    -0.69
    cent
    -0.67
    acca
    -0.65
     guiName
    -0.57
     Warning
    -0.56
    Therefore
    -0.56
    False
    -0.56
    acc
    -0.56
    zai
    -0.55
    POSITIVE LOGITS
    anwhile
    0.75
     tomorrow
    0.71
     whether
    0.70
    nesday
    0.70
    mma
    0.65
     confir
    0.64
     toget
    0.62
    whether
    0.62
     develops
    0.61
     unfolds
    0.61
    Activations Density 0.164%

    No Known Activations