© 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. 3-RES-JB
    11. 10808
    Prev
    Next
    INDEX
    Explanations

    words related to dirty or messy situations

    oai_token-act-pair · gpt-3.5-turbo

    words related to sports and competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.76
    ANCE
    -0.60
    GV
    -0.60
     LX
    -0.60
     SAR
    -0.59
     Boat
    -0.58
    EXP
    -0.58
     ASC
    -0.58
    isu
    -0.58
     USC
    -0.54
    POSITIVE LOGITS
    achusetts
    0.84
    waukee
    0.82
    ographed
    0.78
    hemat
    0.74
    tering
    0.72
    akable
    0.72
    onductor
    0.71
    etting
    0.70
    gage
    0.69
    agues
    0.66
    Activations Density 0.063%

    No Known Activations