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. 0-RES-JB
    6. 19703
    Prev
    Next
    INDEX
    Explanations

    phrases related to storing and retrieval of information

    oai_token-act-pair · gpt-3.5-turbo

    references to stored data or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crit
    -0.74
     Trib
    -0.66
    imp
    -0.66
     Reform
    -0.65
    ador
    -0.64
     Feminist
    -0.64
     Huss
    -0.64
     Dob
    -0.64
     Opportun
    -0.63
    immigration
    -0.63
    POSITIVE LOGITS
     stored
    3.42
     storing
    2.21
     cached
    1.74
     storage
    1.71
     retrieved
    1.61
     Storage
    1.43
     stores
    1.43
    Storage
    1.43
     store
    1.42
     deposited
    1.37
    Activations Density 0.018%

    No Known Activations