© 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. 17631
    Prev
    Next
    INDEX
    Explanations

    specific words or phrases related to products or advertisements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of references to various gods and their associated narratives

    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
     è£ıç
    -0.67
     shoulder
    -0.62
     HSBC
    -0.60
     MU
    -0.57
    ],"
    -0.56
     Notre
    -0.56
     WR
    -0.55
     ACC
    -0.54
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.54
    wcs
    -0.54
    POSITIVE LOGITS
    entimes
    0.75
    ogether
    0.70
    idity
    0.67
    arger
    0.65
     consists
    0.64
     retains
    0.64
     Pradesh
    0.64
    roma
    0.62
     solves
    0.62
    thus
    0.61
    Activations Density 0.398%

    No Known Activations