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. 12-RES-JB
    6. 17762
    Prev
    Next
    INDEX
    Explanations

    digital certificates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    alphanumeric sequences that resemble codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Britann
    -0.74
     eleph
    -0.69
     Levant
    -0.68
     spor
    -0.66
     gears
    -0.65
    anwhile
    -0.64
     Eden
    -0.64
     Titus
    -0.64
     Constantine
    -0.64
     Conway
    -0.64
    POSITIVE LOGITS
    Mp
    1.26
    MQ
    1.26
    ZX
    1.24
    Ul
    1.20
    AAAA
    1.20
    pb
    1.20
    dL
    1.19
    ==
    1.18
    XM
    1.17
    GV
    1.16
    Activations Density 0.036%

    No Known Activations