© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4034
    Prev
    Next
    INDEX
    Explanations

    instances where the word "always" is used

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "always" and its variations, indicating a focus on permanence or habitual actions

    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
    channelAvailability
    -0.74
    Sys
    -0.70
    LESS
    -0.70
    Loading
    -0.67
    aspx
    -0.66
    yo
    -0.66
    Generic
    -0.64
    Lago
    -0.64
    aye
    -0.64
    dm
    -0.62
    POSITIVE LOGITS
     existed
    1.01
     fascinated
    0.99
     dreamed
    0.96
     assumed
    0.88
     regarded
    0.88
     underestimated
    0.86
     seemed
    0.86
     resided
    0.84
     relied
    0.84
     disliked
    0.83
    Activations Density 0.047%

    No Known Activations