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. 3-RES-JB
    6. 22204
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Rein" followed by various suffixes and prefixes

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Rein" and characters named "Hamm" or "Hass"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =#
    -0.72
    teness
    -0.69
    creen
    -0.68
    ''''
    -0.68
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    ny
    -0.67
    ãĥ£
    -0.67
    luaj
    -0.67
    ategory
    -0.66
    opal
    -0.66
    POSITIVE LOGITS
    hardt
    1.05
    roth
    0.92
    acher
    0.90
    stadt
    0.89
    hart
    0.86
    forced
    0.81
    ofer
    0.80
    mington
    0.79
    icht
    0.79
    inger
    0.79
    Activations Density 0.017%

    No Known Activations