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

    Neuronpedia

    Jacobian LensNEW
    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. 5643
    Prev
    Next
    INDEX
    Explanations

    text related to scraps or scavenge

    oai_token-act-pair · gpt-3.5-turbo

    references to scraps and scavenging

    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
    CVE
    -0.79
    igmatic
    -0.74
    secut
    -0.73
     attentive
    -0.69
     conspicuous
    -0.67
    iyah
    -0.66
     uncond
    -0.66
    cest
    -0.65
    secution
    -0.65
    vironments
    -0.64
    POSITIVE LOGITS
    ãĤ¡
    0.85
    atted
    0.84
    bones
    0.84
    shaw
    0.84
    hire
    0.84
    yard
    0.83
    ree
    0.81
     heap
    0.80
    enhagen
    0.79
    dump
    0.76
    Activations Density 0.022%

    No Known Activations