© 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. 6-RES-JB
    11. 14727
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions being taken

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to concerns and attention regarding safety and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fuck
    -0.64
     Pse
    -0.61
     fame
    -0.61
     Beat
    -0.59
    OGR
    -0.57
     Que
    -0.57
    stories
    -0.57
     Chains
    -0.56
     misfortune
    -0.56
     Flo
    -0.56
    POSITIVE LOGITS
    aukee
    0.97
    ļéĨĴ
    0.78
    ername
    0.76
    ģ«
    0.72
    thren
    0.70
    zinski
    0.67
    Ī
    0.65
    ħĭ
    0.65
    ignt
    0.65
    emaker
    0.64
    Activations Density 0.325%

    No Known Activations