© 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. 19292
    Prev
    Next
    INDEX
    Explanations

    people's names often preceded by their titles or aliases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating additional information about a subject or concept

    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
    maxwell
    -0.67
    orest
    -0.61
    anwhile
    -0.60
    rison
    -0.60
    folios
    -0.60
    é¾įå¥ij士
    -0.60
     Banner
    -0.58
    omore
    -0.58
    adena
    -0.58
    ¶ħ
    -0.58
    POSITIVE LOGITS
     happens
    0.92
     known
    0.82
     referred
    0.81
     serves
    0.79
     served
    0.78
     applies
    0.77
    NESS
    0.77
     qualifies
    0.75
     includes
    0.73
     exists
    0.70
    Activations Density 0.102%

    No Known Activations