© 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. 9-RES-JB
    11. 18026
    Prev
    Next
    INDEX
    Explanations

    abstract concepts or principles related to reasoning and arguments

    oai_token-act-pair · gpt-3.5-turbo

    references to logic and reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avez
    -0.70
    eded
    -0.70
    pain
    -0.69
    jri
    -0.67
     Veterans
    -0.67
     Volunte
    -0.64
    artney
    -0.64
    orks
    -0.63
    lain
    -0.63
    rifice
    -0.62
    POSITIVE LOGITS
     reasoning
    0.98
     fallacy
    0.96
     logic
    0.92
     logically
    0.92
     underpin
    0.87
     argument
    0.84
     posit
    0.84
    istically
    0.84
    ynes
    0.83
     puzzles
    0.81
    Activations Density 0.057%

    No Known Activations