© 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. 14598
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "hemp" at various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hemp" and its repetition

    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
    ãĤ¶
    -0.76
    otti
    -0.65
    ysis
    -0.65
     iod
    -0.63
     pian
    -0.60
    cki
    -0.60
    ãĥ´
    -0.60
     faults
    -0.60
    æ©
    -0.59
    gio
    -0.59
    POSITIVE LOGITS
    olicy
    1.08
    earing
    0.88
    manship
    0.86
    raising
    0.80
    ense
    0.77
    skirts
    0.72
    iaries
    0.72
    esm
    0.71
    imity
    0.71
    earance
    0.70
    Activations Density 0.049%

    No Known Activations