© 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. 2-RES-JB
    11. 19552
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to cinematic elements and storytelling techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RESULTS
    -0.31
     Pwr
    -0.28
     Accountability
    -0.28
    enei
    -0.27
     fixme
    -0.25
    ongyang
    -0.25
    NetMessage
    -0.24
    =-=-
    -0.24
     FANTASY
    -0.23
     diplom
    -0.23
    POSITIVE LOGITS
    ãĥ³ãĤ¸
    0.31
    sburg
    0.31
    ardless
    0.30
    iversary
    0.29
    ãģ¾
    0.27
    ibly
    0.27
    ible
    0.26
    æ©
    0.26
    arsity
    0.25
    ãĤ½
    0.25
    Activations Density 10.723%

    No Known Activations