© 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. 2-RES-JB
    11. 17857
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political controversies

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events following a tragedy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lav
    -0.87
     Concent
    -0.85
    leans
    -0.77
    nel
    -0.77
    lain
    -0.76
    eneg
    -0.72
     Nights
    -0.72
    utral
    -0.72
     Wide
    -0.70
    izontal
    -0.68
    POSITIVE LOGITS
    天
    0.71
     samurai
    0.66
    endi
    0.64
     delinquent
    0.64
    ho
    0.63
    ername
    0.62
     fitness
    0.62
    Tok
    0.62
     cos
    0.61
     prediction
    0.60
    Activations Density 0.000%

    No Known Activations