© 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. 5278
    Prev
    Next
    INDEX
    Explanations

    the word "reasons" followed by an explanation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss justifications or explanations

    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
    ibaba
    -0.70
    yss
    -0.67
     likeness
    -0.64
    enged
    -0.60
    semble
    -0.60
    agra
    -0.60
     padd
    -0.59
     Lans
    -0.59
     tatt
    -0.58
     Observer
    -0.58
    POSITIVE LOGITS
    abl
    1.06
     why
    0.94
     reasons
    0.90
    why
    0.87
     unrelated
    0.85
    behind
    0.83
    asons
    0.83
     alone
    0.82
    Reason
    0.79
    atical
    0.77
    Activations Density 0.043%

    No Known Activations