© 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
    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. 13293
    Prev
    Next
    INDEX
    Explanations

    verbs related to causing harm or death

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" highlighting actions or intentions

    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
     hes
    -0.62
     employer
    -0.62
     Riders
    -0.59
     indef
    -0.59
     navig
    -0.59
     discretionary
    -0.59
     cancell
    -0.59
     reactions
    -0.59
     risks
    -0.58
     licences
    -0.58
    POSITIVE LOGITS
    pless
    1.11
    othy
    1.09
    ppers
    1.05
    wered
    1.04
    ggles
    1.02
    pping
    0.99
     satisfy
    0.98
     promote
    0.98
     commemorate
    0.97
    pper
    0.95
    Activations Density 0.308%

    No Known Activations