© 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. 4965
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to different fields of study and classifications

    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
    ammers
    -0.81
    adequ
    -0.79
    avers
    -0.78
    iffs
    -0.76
    lees
    -0.75
    =~
    -0.75
    pees
    -0.75
    appropriately
    -0.74
    aters
    -0.73
    anwhile
    -0.72
    POSITIVE LOGITS
     edition
    0.95
     version
    0.89
     motto
    0.84
     chapter
    0.84
     model
    0.83
     strategy
    0.81
     solution
    0.80
     experience
    0.79
     document
    0.78
     example
    0.78
    Activations Density 0.728%

    No Known Activations