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. 15952
    Prev
    Next
    INDEX
    Explanations

    words related to alternative options or choices

    oai_token-act-pair · gpt-3.5-turbo

    alternative phrases or options presented in a context

    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
     starters
    -0.62
     present
    -0.56
     regards
    -0.55
     retard
    -0.55
     Mum
    -0.55
    lished
    -0.53
     bumps
    -0.53
     fresh
    -0.53
     reserved
    -0.53
     Pwr
    -0.53
    POSITIVE LOGITS
    or
    3.97
    ors
    2.33
    OR
    2.20
    orate
    1.96
    orian
    1.91
    oran
    1.89
    oris
    1.86
    orio
    1.81
    oros
    1.74
    ori
    1.73
    Activations Density 0.027%

    No Known Activations