© 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. 6-RES-JB
    11. 4231
    Prev
    Next
    INDEX
    Explanations

    words related to emptiness or lack of content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blank" in various contexts

    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
    IVERS
    -0.75
    CVE
    -0.74
    annis
    -0.74
    HI
    -0.74
    byn
    -0.73
    tis
    -0.71
    NPR
    -0.70
    IVER
    -0.69
    pora
    -0.69
    GAN
    -0.69
    POSITIVE LOGITS
    eting
    1.13
     slate
    1.12
    ety
    1.00
     stares
    0.91
    etry
    0.89
     blank
    0.81
     spaces
    0.81
    ness
    0.81
    cies
    0.81
     Blank
    0.79
    Activations Density 0.016%

    No Known Activations