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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 23142
    Prev
    Next
    INDEX
    Explanations

    mentions of names of specific places, people, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to relationships and indiscriminate actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORT
    -0.68
    cart
    -0.68
    amara
    -0.68
     Pod
    -0.67
    Marx
    -0.67
    »
    -0.66
     defaults
    -0.65
     dinosaur
    -0.64
    models
    -0.64
     tf
    -0.63
    POSITIVE LOGITS
     Glou
    3.36
     fian
    1.35
     Kou
    1.07
     Antiqu
    1.06
    Clar
    0.92
     Hib
    0.92
     Paraly
    0.88
    phia
    0.86
    Jer
    0.85
     Somerset
    0.84
    Activations Density 0.047%

    No Known Activations