© 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. 6885
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and uncertainties

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the essence or identity of a subject

    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
     Roll
    -0.63
     reflective
    -0.59
     juggling
    -0.55
    icipated
    -0.54
     Hands
    -0.50
     buildup
    -0.50
     Direct
    -0.50
     Ware
    -0.49
     hostage
    -0.49
     particip
    -0.49
    POSITIVE LOGITS
     yes
    1.01
    YES
    0.99
     YES
    0.93
     Nope
    0.90
    yes
    0.89
    Yes
    0.88
    laughs
    0.81
     anyway
    0.80
     answer
    0.80
     Yes
    0.79
    Activations Density 1.506%

    No Known Activations