© 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. 9-RES-JB
    11. 15881
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating strong agreement or support

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong agreement or confirmation

    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
     Welsh
    -0.75
    BALL
    -0.71
     Dynamics
    -0.71
     Romans
    -0.69
     Holmes
    -0.68
     Ballard
    -0.60
     Jobs
    -0.60
     Masters
    -0.58
     Icelandic
    -0.58
     Abyss
    -0.58
    POSITIVE LOGITS
    ourced
    1.22
    olute
    1.19
    pec
    1.18
    ounding
    1.16
    olver
    1.16
    umption
    1.14
    olutely
    1.10
    ound
    1.08
    ourcing
    1.08
    pell
    1.07
    Activations Density 0.010%

    No Known Activations