© 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. 9-RES-JB
    11. 23312
    Prev
    Next
    INDEX
    Explanations

    phrases related to solutions to conflicts

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emphasis or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perfume
    -0.84
     starve
    -0.83
     coral
    -0.80
     fancy
    -0.80
     fetish
    -0.79
     conscious
    -0.79
     dolphin
    -0.79
     mint
    -0.78
     displacement
    -0.78
     invisible
    -0.76
    POSITIVE LOGITS
    âĢ
    1.59
    Comment
    1.52
    RAW
    1.46
    Asked
    1.45
    Discuss
    1.44
    Posted
    1.44
    Resp
    1.42
    Comments
    1.42
    ________________________________________________________________
    1.42
    (*
    1.42
    Activations Density 0.309%

    No Known Activations