© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2080
    Prev
    Next
    INDEX
    Explanations

    text patterns related to the topic of legal or political discourse

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" and its usage in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Edit
    -0.83
    Thom
    -0.76
    uin
    -0.76
    Versions
    -0.75
    Options
    -0.74
    events
    -0.74
    Ali
    -0.74
     Emails
    -0.73
    coins
    -0.73
     edits
    -0.73
    POSITIVE LOGITS
     fascinating
    1.03
     huge
    1.02
     lot
    1.00
     wonderful
    1.00
     cornerstone
    0.99
     relatively
    0.99
     hugely
    0.98
     reminder
    0.97
     fixture
    0.96
     terrific
    0.96
    Activations Density 0.301%

    No Known Activations