© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 16993
    Prev
    Next
    INDEX
    Explanations

    terms related to technological payloads, especially in the context of aerospace and software

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "payload" within a technical context

    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
    lex
    -0.72
     Rite
    -0.68
    isms
    -0.68
    ista
    -0.67
    ism
    -0.66
    uve
    -0.66
     Karma
    -0.65
    ovan
    -0.65
     Seraph
    -0.65
    baum
    -0.65
    POSITIVE LOGITS
     payload
    0.98
    emouth
    0.76
    ngth
    0.74
    sburg
    0.71
    ilitary
    0.70
     teasp
    0.70
     sidx
    0.70
    ODUCT
    0.66
    rss
    0.66
    GY
    0.65
    Activations Density 0.050%

    No Known Activations