© 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. 0-RES-JB
    11. 4097
    Prev
    Next
    INDEX
    Explanations

    words related to support or promotion of a cause or belief

    oai_token-act-pair · gpt-3.5-turbo

    discussions about advocacy or recommendations in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exit
    -0.80
     processing
    -0.78
     identification
    -0.78
     interaction
    -0.77
     stunning
    -0.76
     background
    -0.75
     chance
    -0.74
     release
    -0.74
     alert
    -0.72
     timing
    -0.70
    POSITIVE LOGITS
     advocated
    2.22
     preached
    2.08
     advocating
    1.88
     preach
    1.70
     prescribe
    1.62
     instituted
    1.59
     coined
    1.38
     debated
    1.32
     pioneered
    1.31
     preaching
    1.30
    Activations Density 0.076%

    No Known Activations