© 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. 1-RES-JB
    11. 13487
    Prev
    Next
    INDEX
    Explanations

    keywords related to stockpiling or hoarding items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stockpiling and storing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adv
    -0.77
     Independent
    -0.71
    nor
    -0.67
    hood
    -0.67
    ploma
    -0.67
    article
    -0.65
    win
    -0.65
    de
    -0.63
     Pall
    -0.63
    views
    -0.62
    POSITIVE LOGITS
     stockp
    1.38
     stockpile
    1.31
    ãĥ¼ãĥĨãĤ£
    1.08
     stash
    0.93
     holdings
    0.91
    apons
    0.84
    itures
    0.83
    igham
    0.82
    ickr
    0.79
     bunker
    0.78
    Activations Density 0.007%

    No Known Activations