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. 17496
    Prev
    Next
    INDEX
    Explanations

    biographical information about sports players

    oai_token-act-pair · gpt-3.5-turbo

    references to statistics and rankings in sports

    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
    ctrl
    -0.80
    Reviewer
    -0.76
    sth
    -0.75
     reconc
    -0.66
    idays
    -0.66
    opath
    -0.64
     remem
    -0.62
     listeners
    -0.62
    iven
    -0.62
    loe
    -0.61
    POSITIVE LOGITS
    advertising
    0.88
     Fresno
    0.81
    ometown
    0.78
     LSU
    0.76
    anova
    0.75
     rookie
    0.74
    Born
    0.73
     fullback
    0.72
     Defensive
    0.71
     Cameroon
    0.71
    Activations Density 0.160%

    No Known Activations