© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10920
    Prev
    Next
    INDEX
    Explanations

    mentions of government policies and international affairs

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to economic and industrial statistics

    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
    andel
    -0.84
    ollah
    -0.67
     vengeance
    -0.65
     RAND
    -0.64
     Cec
    -0.59
    iot
    -0.58
     Roc
    -0.58
     illusion
    -0.57
    erity
    -0.57
     Riv
    -0.57
    POSITIVE LOGITS
    liest
    1.02
    angered
    0.82
     destinations
    0.81
    iest
    0.81
     respectively
    0.81
     surveyed
    0.80
    ottest
    0.74
    natureconservancy
    0.74
     category
    0.74
    Ü
    0.74
    Activations Density 0.763%

    No Known Activations