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. 7301
    Prev
    Next
    INDEX
    Explanations

    phrases related to rescue or help activity

    oai_token-act-pair · gpt-3.5-turbo

    references to questions or issues

    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
     Cum
    -0.61
     Mamm
    -0.61
    Rat
    -0.59
     Ath
    -0.57
     Internet
    -0.56
     Arlington
    -0.55
     Crab
    -0.55
     malware
    -0.55
     opinion
    -0.55
     strateg
    -0.55
    POSITIVE LOGITS
    ues
    4.79
    ued
    2.94
    UES
    2.65
    uing
    2.59
    ue
    2.56
    UE
    2.45
    uers
    2.16
    uer
    1.80
    uel
    1.72
    uez
    1.42
    Activations Density 0.006%

    No Known Activations