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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 4849
    Prev
    Next
    INDEX
    Explanations

    keywords related to behavioral science and psychology

    oai_token-act-pair · gpt-3.5-turbo

    references to behavioral concepts and terms

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

    No Comments

    Negative Logits
    shall
    -0.93
    eous
    -0.91
    enthal
    -0.82
    eem
    -0.78
    bur
    -0.77
    nah
    -0.73
    zzo
    -0.73
    ARDS
    -0.73
    urat
    -0.72
    large
    -0.72
    POSITIVE LOGITS
     behavioral
    1.08
    avior
    1.04
     behavioural
    0.93
     behavi
    0.92
     Behavioral
    0.89
     conditioning
    0.88
     biology
    0.86
     genetics
    0.85
     sciences
    0.85
     biologists
    0.85
    Activations Density 0.013%

    No Known Activations