© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 3640
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to deep analysis or interpretation

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "deeper" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EED
    -0.80
    ULE
    -0.78
     WATCHED
    -0.73
    DOM
    -0.73
    EVA
    -0.73
    advertising
    -0.71
     Athlet
    -0.70
    OK
    -0.70
    ILLE
    -0.69
    SR
    -0.69
    POSITIVE LOGITS
     deeper
    1.05
     depth
    0.98
     depths
    0.91
     penetration
    0.88
    depth
    0.88
     insight
    0.86
     penetrating
    0.85
     horizont
    0.85
     maturity
    0.84
     deep
    0.83
    Activations Density 0.006%

    No Known Activations