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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 19054
    Prev
    Next
    INDEX
    Explanations

    financial transactions or control mechanisms, particularly related to checks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to verification or examination processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     Hots
    -0.84
    BLE
    -0.80
    CTV
    -0.65
     FANT
    -0.62
     Picture
    -0.61
    ãĥĨãĤ£
    -0.61
     Lear
    -0.60
    wcs
    -0.58
     DRAG
    -0.58
     ILCS
    -0.58
    POSITIVE LOGITS
    lists
    1.22
    boxes
    1.13
    ums
    1.11
    list
    1.07
    points
    1.06
    box
    1.04
    er
    1.03
    ups
    0.99
    point
    0.97
    outs
    0.96
    Activations Density 0.040%

    No Known Activations