© 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. 10-RES-JB
    11. 12798
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing opinions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "It" and variations of its usage in sentences

    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
     Mole
    -0.58
     Ther
    -0.58
     wielding
    -0.57
     Bunker
    -0.57
    WARE
    -0.56
     2048
    -0.56
    xus
    -0.56
    arthed
    -0.55
     Shutterstock
    -0.55
    warning
    -0.55
    POSITIVE LOGITS
     depends
    1.32
     hurts
    1.24
     ain
    1.22
     happens
    1.19
     sucks
    1.18
     doesn
    1.17
     wasn
    1.16
     boils
    1.16
    zbollah
    1.15
     bothers
    1.15
    Activations Density 0.179%

    No Known Activations