© 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. 5475
    Prev
    Next
    INDEX
    Explanations

    phrases related to paper and paper-based products

    oai_token-act-pair · gpt-3.5-turbo

    references to paper and its various contexts and uses

    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
    cffffcc
    -0.85
    ivals
    -0.82
    CVE
    -0.79
    ostic
    -0.73
    oise
    -0.72
    ostics
    -0.72
    Sax
    -0.70
    Enlarge
    -0.69
    «ĺ
    -0.68
    essee
    -0.67
    POSITIVE LOGITS
    clip
    1.31
     towels
    1.19
    clips
    1.04
     towel
    0.99
    backs
    0.87
    pee
    0.86
    thin
    0.84
     pus
    0.84
    maid
    0.81
    brush
    0.80
    Activations Density 0.030%

    No Known Activations