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. 0-RES-JB
    6. 21637
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "ipped"

    oai_token-act-pair · gpt-3.5-turbo

    words related to being equipped or prepared

    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
     thereof
    -0.76
     divers
    -0.71
     rhy
    -0.68
     hist
    -0.63
     DA
    -0.61
     fame
    -0.60
     concrete
    -0.60
     de
    -0.60
     quant
    -0.59
     cast
    -0.59
    POSITIVE LOGITS
    ipped
    3.93
    ipping
    3.88
    ips
    2.27
    ippers
    1.88
    IPP
    1.88
    ipper
    1.75
    ippy
    1.71
    IPS
    1.68
    ipp
    1.61
    ip
    1.59
    Activations Density 0.022%

    No Known Activations