© 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. 6-RES-JB
    11. 3691
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Parnell"

    oai_token-act-pair · gpt-3.5-turbo

    names or mentions of individuals, particularly those with the surname "Parnell."

    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
    kson
    -0.62
     Mub
    -0.60
     prevailing
    -0.59
    cipl
    -0.59
     Fract
    -0.58
     deaf
    -0.57
    lda
    -0.57
    BILITY
    -0.56
     htt
    -0.56
    pared
    -0.55
    POSITIVE LOGITS
    ataka
    1.20
    igans
    0.95
    aby
    0.95
    ings
    0.92
    ement
    0.91
    alos
    0.91
    ances
    0.88
    ival
    0.88
    ivals
    0.88
    aval
    0.87
    Activations Density 0.021%

    No Known Activations