Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22163
    Prev
    Next
    INDEX
    Explanations

    terms related to hoarding or accumulating a reserve of items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stockpiling and storing resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adv
    -0.74
    obo
    -0.69
    english
    -0.65
    ĪĴ
    -0.63
    hood
    -0.61
    alities
    -0.61
     imperson
    -0.61
     Outs
    -0.61
    nom
    -0.61
    odor
    -0.60
    POSITIVE LOGITS
     stockpile
    1.12
     stockp
    1.11
     stash
    0.98
    ãĥ¼ãĥĨãĤ£
    0.96
    ickr
    0.92
     shelves
    0.87
     hoard
    0.87
    ructure
    0.85
     holdings
    0.85
     stocked
    0.84
    Activations Density 0.020%

    No Known Activations