© 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. 8-RES-JB
    11. 10849
    Prev
    Next
    INDEX
    Explanations

    words related to metal and materials

    oai_token-act-pair · gpt-3.5-turbo

    terms related to types of materials or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     detrim
    -0.67
     envelope
    -0.64
    steen
    -0.63
     TTL
    -0.63
    Ħ¢
    -0.63
     Mahjong
    -0.61
     surv
    -0.60
     pleasures
    -0.60
    */(
    -0.59
     enjoyment
    -0.59
    POSITIVE LOGITS
    ritic
    0.89
    ãĤ¡
    0.88
    xual
    0.83
    ogl
    0.76
    iction
    0.75
    eteria
    0.75
    ognitive
    0.75
    ulty
    0.74
    urgy
    0.74
    meric
    0.74
    Activations Density 0.150%

    No Known Activations