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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2395
    Prev
    Next
    INDEX
    Explanations

    phrases related to intervention or taking action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to protective actions or measures

    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
     Hassan
    -0.70
    ecd
    -0.69
     Codex
    -0.68
    ausible
    -0.67
    ivable
    -0.65
    noticed
    -0.64
     faces
    -0.63
     Faces
    -0.63
    igm
    -0.63
    onym
    -0.62
    POSITIVE LOGITS
     wreck
    0.97
     interfere
    0.95
     help
    0.94
     demol
    0.93
     alleviate
    0.92
     propel
    0.91
     wre
    0.90
     stabilize
    0.89
     suffice
    0.88
     devast
    0.88
    Activations Density 0.827%

    No Known Activations