© 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. 4457
    Prev
    Next
    INDEX
    Explanations

    references to spatial relationships involving the word "next"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "next."

    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
    lee
    -0.70
     Feldman
    -0.66
    ocker
    -0.65
    bach
    -0.64
     Legions
    -0.64
    lees
    -0.63
    hist
    -0.63
     Hebdo
    -0.63
     Sinai
    -0.62
    ribution
    -0.62
    POSITIVE LOGITS
     millenn
    0.95
    etheless
    0.91
     week
    0.89
     step
    0.87
    ĻĤ
    0.85
     srf
    0.82
     installment
    0.80
     neighb
    0.79
     morning
    0.79
     generation
    0.78
    Activations Density 0.040%

    No Known Activations