© 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. 6-RES-JB
    11. 13953
    Prev
    Next
    INDEX
    Explanations

    reasons or justifications for actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reasons or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eps
    -0.80
     ILCS
    -0.79
    cles
    -0.78
    ros
    -0.77
    jab
    -0.77
    chn
    -0.76
    Pixel
    -0.76
    nets
    -0.76
    thumbnails
    -0.74
    chin
    -0.74
    POSITIVE LOGITS
     why
    1.02
     inaction
    0.90
     upholding
    0.81
     existence
    0.79
     dismissal
    0.77
     supremacy
    0.76
     deliberations
    0.75
     hating
    0.75
     disagreement
    0.74
     dismissing
    0.74
    Activations Density 0.065%

    No Known Activations