© 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. 8-RES-JB
    11. 22433
    Prev
    Next
    INDEX
    Explanations

    step-by-step instructions or guides

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to step-by-step processes or guides

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idays
    -0.78
    atform
    -0.77
    ropolitan
    -0.76
    izons
    -0.75
    elaide
    -0.70
     Fiscal
    -0.70
    nesty
    -0.68
    assadors
    -0.66
     Commissioner
    -0.66
    oubted
    -0.66
    POSITIVE LOGITS
     technique
    1.17
     routines
    1.17
     tricks
    1.15
     techniques
    1.05
     trick
    1.00
     procedure
    0.99
     Instruct
    0.97
     Technique
    0.97
     basics
    0.93
     chore
    0.93
    Activations Density 0.729%

    No Known Activations