© 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. 16820
    Prev
    Next
    INDEX
    Explanations

    references to things that are no longer functional or in use

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dead" in various contexts

    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
    ĸļ
    -0.78
    ECA
    -0.74
    orney
    -0.73
    ãĥ´ãĤ¡
    -0.72
    Catalog
    -0.71
    Ô
    -0.68
     CLSID
    -0.66
    ATIONS
    -0.66
    ãĤ¢ãĥ«
    -0.64
    zzle
    -0.64
    POSITIVE LOGITS
    beat
    1.02
    weight
    1.00
    locked
    0.99
    spin
    0.98
    liest
    0.96
    lier
    0.92
    heading
    0.91
     carc
    0.87
    lift
    0.87
     reckoning
    0.86
    Activations Density 0.027%

    No Known Activations