© 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. 1372
    Prev
    Next
    INDEX
    Explanations

    phrases related to highlighting, drawing attention, or emphasizing specific information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate pointing or referring to specific subjects or themes

    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
    lance
    -0.75
    hop
    -0.74
    ynthesis
    -0.71
    soever
    -0.70
     behav
    -0.69
     lett
    -0.68
    MAP
    -0.67
    unte
    -0.66
     operates
    -0.65
    mediated
    -0.65
    POSITIVE LOGITS
    othy
    0.86
    asty
    0.74
    odan
    0.70
     Genocide
    0.68
    obin
    0.66
     Bullets
    0.65
     Dud
    0.65
     infinity
    0.64
     indicate
    0.63
    entin
    0.61
    Activations Density 0.089%

    No Known Activations