Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 22287
    Prev
    Next
    INDEX
    Explanations

    references to human rights organizations, specifically "HRW (Human Rights Watch)"

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights organizations and their activities

    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
    lihood
    -0.88
    struct
    -0.79
    cart
    -0.74
    eu
    -0.69
     ç¥ŀ
    -0.69
    cence
    -0.68
     Wand
    -0.67
    sta
    -0.67
    eers
    -0.67
     Tasman
    -0.67
    POSITIVE LOGITS
    RR
    1.03
    senal
    1.03
    utherford
    0.93
    Ds
    0.91
    VO
    0.91
    ANGE
    0.87
    ands
    0.87
    APH
    0.87
    anges
    0.85
    andom
    0.84
    Activations Density 0.044%

    No Known Activations