© 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. 18447
    Prev
    Next
    INDEX
    Explanations

    phrases related to race or skin color

    oai_token-act-pair · gpt-3.5-turbo

    references to people of color

    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
    •Another quick list

    No Comments

    Negative Logits
     preparations
    -0.60
     hallucinations
    -0.58
    Reloaded
    -0.58
    Features
    -0.57
     symptoms
    -0.57
     rounds
    -0.57
     veins
    -0.56
     seams
    -0.54
     needles
    -0.54
    thumbnails
    -0.54
    POSITIVE LOGITS
    ortunately
    0.96
     course
    0.85
    icial
    0.80
     whom
    0.75
    pires
    0.74
    course
    0.70
    iciency
    0.67
    idth
    0.66
    sted
    0.66
    ramer
    0.65
    Activations Density 0.091%

    No Known Activations