© 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. 15833
    Prev
    Next
    INDEX
    Explanations

    phrases related to industrial organizations or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to industrial processes or provisions

    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
     Logged
    -0.68
    Cow
    -0.65
    Indian
    -0.65
     Duterte
    -0.63
    Ear
    -0.62
    India
    -0.61
     Rivera
    -0.61
    Rs
    -0.60
     shorts
    -0.60
    taboola
    -0.59
    POSITIVE LOGITS
    heit
    1.24
    wagen
    1.04
     Zeit
    1.00
     Volks
    0.94
     von
    0.88
     Ges
    0.82
     Bundes
    0.82
     Psychiat
    0.81
    krit
    0.80
    ÃŁ
    0.80
    Activations Density 0.159%

    No Known Activations