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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17298
    Prev
    Next
    INDEX
    Explanations

    references to the sports team "Rams"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Rams football team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    judicial
    -0.79
    lly
    -0.74
     causal
    -0.67
     coronary
    -0.66
    ternity
    -0.66
    CLASSIFIED
    -0.64
     disadvant
    -0.62
     testim
    -0.62
     whistlebl
    -0.60
     bellig
    -0.59
    POSITIVE LOGITS
     Rams
    1.06
    aic
    0.96
    mers
    0.93
    borg
    0.86
    istani
    0.84
    eco
    0.84
    opa
    0.84
    seys
    0.78
    oran
    0.77
    sburg
    0.77
    Activations Density 0.019%

    No Known Activations