Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18730
    Prev
    Next
    INDEX
    Explanations

    information related to medical conditions or research studies involving people

    oai_token-act-pair · gpt-3.5-turbo

    references to human subjects or individuals in medical or psychological contexts

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

    No Comments

    Negative Logits
    ãĥķãĤ©
    -0.88
    Chain
    -0.78
    Accessory
    -0.78
    èĢħ
    -0.78
    Rules
    -0.77
    Shut
    -0.77
     actionGroup
    -0.77
    Viol
    -0.76
    é»Ĵ
    -0.75
    Politics
    -0.75
    POSITIVE LOGITS
     diagnosed
    1.09
     aged
    1.03
     ingested
    1.01
     undergoing
    1.00
    opausal
    1.00
     hormone
    0.96
     studied
    0.92
     hospitalized
    0.92
     enrolled
    0.89
     vaccinated
    0.89
    Activations Density 0.198%

    No Known Activations