© 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. 10-RES-JB
    11. 9287
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions occurring in the future

    oai_token-act-pair · gpt-3.5-turbo

    the word "before" and its contextual usage associated with time-related conditions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.77
    aez
    -0.76
    ologic
    -0.74
    ãĤ¤
    -0.74
    Force
    -0.71
    ãĥ¼ãĥ
    -0.69
    agi
    -0.68
    Ļ
    -0.68
    quist
    -0.67
    ©¶æ
    -0.67
    POSITIVE LOGITS
     sunrise
    1.19
     dawn
    1.10
     midnight
    1.09
     noon
    1.07
     anyone
    0.99
     sunset
    0.98
     anybody
    0.90
     expiration
    0.89
     Christmas
    0.87
     embark
    0.87
    Activations Density 0.069%

    No Known Activations