© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 972
    Prev
    Next
    INDEX
    Explanations

    phrases related to cause and effect, specifically highlighting the triggering action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating cause-and-effect relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogun
    -0.66
    rament
    -0.65
    alty
    -0.65
    okin
    -0.62
    ilion
    -0.61
    ufact
    -0.61
    anon
    -0.60
     specialists
    -0.58
     Countdown
    -0.57
     Clarks
    -0.57
    POSITIVE LOGITS
    ãĥĥãĥī
    0.82
    ________________________________________________________________
    0.75
    Pub
    0.72
    Produ
    0.67
    shape
    0.64
    SPONSORED
    0.64
    PsyNetMessage
    0.64
    èĥ
    0.63
     prompts
    0.62
    nings
    0.62
    Activations Density 0.015%

    No Known Activations