© 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. 8-RES-JB
    11. 24159
    Prev
    Next
    INDEX
    Explanations

    words related to imagination, conjuring images, and speculative scenarios

    oai_token-act-pair · gpt-3.5-turbo

    words related to conjuring or evoking concepts and imagery

    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
    FINE
    -0.69
    BACK
    -0.68
    HEAD
    -0.66
    PDATE
    -0.65
     Scots
    -0.63
     Chow
    -0.63
     refinement
    -0.62
    holder
    -0.60
    DAQ
    -0.60
    EMOTE
    -0.60
    POSITIVE LOGITS
    ured
    1.43
    uration
    1.33
    urations
    1.26
    aled
    1.25
    urer
    1.18
    ugal
    1.16
    urers
    1.15
    unct
    1.13
    ures
    1.11
    orious
    1.11
    Activations Density 0.081%

    No Known Activations