© 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. 7-RES-JB
    11. 24157
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or states that involve some sort of operation or change

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their associated actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mermaid
    -0.68
     IT
    -0.67
     Fasc
    -0.67
     sincerity
    -0.61
     Things
    -0.61
     Hands
    -0.61
     Romantic
    -0.61
     Proud
    -0.60
     Dinosaur
    -0.60
     Crazy
    -0.60
    POSITIVE LOGITS
     reverted
    1.03
     reapp
    0.95
     subsequently
    0.92
     resumed
    0.92
     regained
    0.87
     retained
    0.86
     replaced
    0.82
     accounted
    0.82
     relocated
    0.81
     returned
    0.79
    Activations Density 0.598%

    No Known Activations