© 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. 3032
    Prev
    Next
    INDEX
    Explanations

    the word "tomorrow"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "tomorrow."

    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
    ochet
    -0.81
    leeve
    -0.81
    hips
    -0.74
    onne
    -0.72
    ordes
    -0.72
    egal
    -0.70
    ership
    -0.70
    hip
    -0.66
    ocker
    -0.66
    aughed
    -0.66
    POSITIVE LOGITS
     morning
    1.42
     afternoon
    1.29
     night
    1.16
     evening
    1.13
     mornings
    1.08
    morning
    1.04
     nights
    0.96
    night
    0.92
    days
    0.91
     NIGHT
    0.89
    Activations Density 0.017%

    No Known Activations