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

    Neuronpedia

    Jacobian LensNEW
    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. 17862
    Prev
    Next
    INDEX
    Explanations

    neuronal noise and false positives, as it does not show consistent activation patterns for specific types of information in the provided text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of serious offenses and substantial events

    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
     counting
    -0.69
     luck
    -0.66
     covenant
    -0.66
     ramps
    -0.65
     escal
    -0.64
     Deluxe
    -0.63
     star
    -0.63
     dolphin
    -0.63
     placement
    -0.62
     Crystal
    -0.62
    POSITIVE LOGITS
    RAW
    1.13
    Updated
    1.06
    Published
    1.03
    Advertisements
    1.01
    Cath
    0.98
    TOR
    0.98
    Associated
    0.96
    Thomas
    0.95
    Section
    0.95
    Posted
    0.95
    Activations Density 0.279%

    No Known Activations