© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 177
    Prev
    Next
    INDEX
    Explanations

    differences in characteristics or behaviors based on economic or health-related factors

    oai_token-act-pair · gpt-3.5-turbo

    references to economic factors and their impact on social behaviors and health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.64
    atever
    -0.64
     insanity
    -0.60
     unanim
    -0.60
    landish
    -0.59
     Nicaragua
    -0.59
     whistlebl
    -0.59
     Genie
    -0.57
     confir
    -0.57
     myster
    -0.57
    POSITIVE LOGITS
     than
    1.43
    than
    1.13
     relative
    1.09
     compared
    1.04
     overall
    0.97
     (>
    0.96
     (~
    0.91
     whereas
    0.91
     (<
    0.89
     thereby
    0.85
    Activations Density 0.267%

    No Known Activations