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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 5599
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    references to personal pronouns

    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
    ono
    -0.66
    onis
    -0.64
    odor
    -0.59
    Rex
    -0.58
    yles
    -0.57
    ģ«
    -0.57
    course
    -0.55
    nexus
    -0.55
    payers
    -0.55
    ardon
    -0.55
    POSITIVE LOGITS
     arrived
    0.94
     transitioned
    0.90
     visited
    0.84
     entered
    0.84
     debuted
    0.83
     ventured
    0.82
     slightest
    0.81
     toured
    0.81
     exited
    0.80
    'd
    0.80
    Activations Density 0.140%

    No Known Activations