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. 6966
    Prev
    Next
    INDEX
    Explanations

    words related to synthesis or synapses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "syn" and its variations, indicating a focus on synonyms or synaptic terminology

    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
    ORED
    -1.02
    aneers
    -0.79
    IVE
    -0.77
     bearer
    -0.75
    200000
    -0.72
    sburg
    -0.71
    DERR
    -0.71
    ardless
    -0.71
    ij士
    -0.70
    een
    -0.70
    POSITIVE LOGITS
    agog
    1.19
    agogue
    1.15
    apse
    1.09
    apses
    1.02
    opsis
    1.01
    chron
    0.93
    onyms
    0.92
     syn
    0.91
    ths
    0.91
    onym
    0.89
    Activations Density 0.014%

    No Known Activations