© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6409
    Prev
    Next
    INDEX
    Explanations

    words related to fine powdery substances

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of powder

    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
     Democr
    -0.77
    nesota
    -0.73
    ĻĤ
    -0.72
    ocene
    -0.71
    obal
    -0.68
    egal
    -0.65
     Robot
    -0.64
    ndra
    -0.64
     Defenders
    -0.63
    OVA
    -0.62
    POSITIVE LOGITS
     powd
    0.93
    stals
    0.92
    powder
    0.90
    roleum
    0.82
     coating
    0.81
     powder
    0.76
     coated
    0.74
     residue
    0.74
    puff
    0.73
    hene
    0.72
    Activations Density 0.032%

    No Known Activations