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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13530
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases emphasizing location or position

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" and its occurrences as a prominent article in various 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
    SPONSORED
    -0.81
     namely
    -0.69
     resided
    -0.69
    CVE
    -0.69
    ,...
    -0.66
     hereby
    -0.66
    cu
    -0.66
    fulness
    -0.65
    soever
    -0.65
    onse
    -0.64
    POSITIVE LOGITS
     fray
    1.12
     proverbial
    1.11
     same
    1.03
     forefront
    1.02
     realm
    0.93
     brink
    0.92
     confines
    0.87
     latter
    0.87
    atre
    0.83
     norm
    0.83
    Activations Density 0.301%

    No Known Activations