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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 7304
    Prev
    Next
    INDEX
    Explanations

    phrases related to faith and religious concepts

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "hands" or "arms" and their symbolic uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mex
    -0.69
     skelet
    -0.66
     Rossi
    -0.66
    aminer
    -0.66
    irez
    -0.65
    inventoryQuantity
    -0.64
    ococ
    -0.62
     Pepe
    -0.62
    legate
    -0.62
     Painter
    -0.62
    POSITIVE LOGITS
    angs
    3.06
    aith
    2.59
    anging
    1.88
    hearted
    1.48
    athed
    1.20
     Covenant
    1.13
    lust
    1.11
    aths
    0.97
    esides
    0.83
    falls
    0.81
    Activations Density 0.029%

    No Known Activations