© 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. 4975
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical thinking and morality

    oai_token-act-pair · gpt-3.5-turbo

    statements about societal beliefs and perceptions

    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
     sidx
    -0.67
    ioch
    -0.67
    ierrez
    -0.65
    idav
    -0.61
    nsic
    -0.61
    cellaneous
    -0.60
    reet
    -0.60
    ktop
    -0.57
    azeera
    -0.57
    yrinth
    -0.57
    POSITIVE LOGITS
    acea
    0.83
     paradise
    0.76
     worthwhile
    0.73
    opathy
    0.73
     evils
    0.72
     somehow
    0.72
     inferior
    0.69
     superiority
    0.67
     acceptable
    0.66
     superior
    0.66
    Activations Density 1.066%

    No Known Activations