© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2720
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing disappointment or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    negative statements related to actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marina
    -0.62
     Juda
    -0.60
     gradually
    -0.60
     periodically
    -0.59
    udo
    -0.58
     Kafka
    -0.57
     Kraft
    -0.56
     Abbas
    -0.56
     Liberty
    -0.55
     Parad
    -0.55
    POSITIVE LOGITS
     anymore
    1.41
    âĢ
    1.28
    ̶
    1.17
    âľ
    1.13
    *.
    1.09
    \.
    1.04
    âĺ
    1.03
    âķ
    1.03
    ãĢ
    1.03
     nor
    1.02
    Activations Density 0.506%

    No Known Activations