© 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 EvalsExportsinterp-engineNEWAPI 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. 9645
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority or actions taken against something or someone

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government enforcement actions or restrictions

    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
    cius
    -0.71
    lled
    -0.67
    chn
    -0.66
    UNCH
    -0.64
    FORM
    -0.64
    zza
    -0.64
    astern
    -0.63
    CE
    -0.63
    WC
    -0.62
    lda
    -0.61
    POSITIVE LOGITS
    s
    2.31
    ski
    1.30
    sburg
    1.25
    sb
    1.21
    sand
    1.18
    sie
    1.16
    sf
    1.13
    sburgh
    1.08
    ship
    1.08
    sg
    1.07
    Activations Density 0.133%

    No Known Activations