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. 2-RES-JB
    6. 10847
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of 'pad', which could be related to various devices or objects such as a mousepad, gamepad, launchpad, or keypads

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of computer input devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marketable
    -0.66
    ews
    -0.65
    IGH
    -0.64
    IRD
    -0.64
    IGHTS
    -0.63
     Cold
    -0.62
     LORD
    -0.61
     Angel
    -0.61
     Bears
    -0.58
     Brit
    -0.58
    POSITIVE LOGITS
    pad
    1.13
    awan
    0.98
    Pad
    0.91
    rice
    0.86
    rollers
    0.82
    rod
    0.82
    ropri
    0.82
    oute
    0.81
    gery
    0.81
    rag
    0.80
    Activations Density 0.006%

    No Known Activations