© 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. 2933
    Prev
    Next
    INDEX
    Explanations

    words related to physical attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    words denoting various past participle verb forms

    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
    anches
    -0.76
    Trade
    -0.74
    involved
    -0.74
    nesota
    -0.72
    forums
    -0.71
    ledge
    -0.70
    estamp
    -0.70
    trade
    -0.70
    osponsors
    -0.70
    ideo
    -0.69
    POSITIVE LOGITS
    gling
    0.82
    ness
    0.77
     tir
    0.74
     Brach
    0.70
     contra
    0.70
    glers
    0.69
    adoes
    0.67
     omn
    0.66
    irection
    0.66
     pup
    0.65
    Activations Density 0.120%

    No Known Activations