© 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. 14753
    Prev
    Next
    INDEX
    Explanations

    short phrases or clauses beginning with "there is" or "there are"

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text markers

    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
    farious
    -0.70
    arthy
    -0.63
     destro
    -0.62
    iterranean
    -0.59
    è¦ļéĨĴ
    -0.59
    ',"
    -0.58
    existent
    -0.58
    ],"
    -0.57
    ocobo
    -0.57
    "—
    -0.56
    POSITIVE LOGITS
    cknowled
    0.59
     largeDownload
    0.53
     Leader
    0.49
    oret
    0.49
     Remastered
    0.49
     Warp
    0.48
    SCP
    0.48
     Orbit
    0.48
     Shot
    0.48
    resy
    0.47
    Activations Density 0.441%

    No Known Activations