© 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. 7-RES-JB
    11. 20876
    Prev
    Next
    INDEX
    Explanations

    words related to explanations or justifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve explanations or justifications for beliefs or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lator
    -0.90
    ymph
    -0.77
     Roller
    -0.75
    iece
    -0.66
    robe
    -0.64
    ograph
    -0.63
    aughed
    -0.61
    wana
    -0.60
     Juda
    -0.60
    ãĤ¤ãĥĪ
    -0.60
    POSITIVE LOGITS
    soever
    1.01
     why
    0.80
     exactly
    0.79
     WHY
    0.77
    why
    0.75
    abouts
    0.73
     bother
    0.69
     they
    0.68
    eve
    0.67
    iterranean
    0.65
    Activations Density 0.039%

    No Known Activations