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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 9433
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming and technical concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to computational processes and information theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Acad
    -0.73
    Nation
    -0.71
    Website
    -0.69
     Mehran
    -0.69
    HQ
    -0.69
     advoc
    -0.66
     municip
    -0.66
     bible
    -0.66
     Emirates
    -0.66
    DonaldTrump
    -0.66
    POSITIVE LOGITS
     parameter
    0.91
     interval
    0.90
    irection
    0.88
    ()
    0.88
     entropy
    0.86
     modifier
    0.86
     function
    0.84
     mode
    0.84
     invari
    0.84
     Boolean
    0.83
    Activations Density 0.764%

    No Known Activations