© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 3042
    Prev
    Next
    INDEX
    Explanations

    command-related instructions or code snippets

    oai_token-act-pair · gpt-3.5-turbo

    commands related to setting configurations or parameters in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.80
     Souls
    -0.70
    sylvania
    -0.67
     Schwe
    -0.67
    çī
    -0.66
    ä¼
    -0.66
    PH
    -0.65
    059
    -0.65
    ç«
    -0.65
    past
    -0.63
    POSITIVE LOGITS
    tle
    0.94
    ter
    0.90
    ters
    0.86
    env
    0.85
    tering
    0.85
    uid
    0.84
     forth
    0.81
    Timeout
    0.80
    cookie
    0.75
    TING
    0.74
    Activations Density 0.033%

    No Known Activations