© 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. 0-RES-JB
    6. 12153
    Prev
    Next
    INDEX
    Explanations

    names related to media or entertainment

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Bl" or related uses of the prefix in various contexts

    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
     ante
    -0.72
     deduct
    -0.71
     dining
    -0.66
     vegetable
    -0.66
     oct
    -0.65
     marg
    -0.65
     reckoned
    -0.64
     induct
    -0.64
     lizard
    -0.64
     gestation
    -0.63
    POSITIVE LOGITS
    Bl
    3.65
    bl
    2.23
     Bl
    2.10
    BL
    1.95
     BL
    1.60
     bl
    1.45
     Blanc
    1.42
    Ble
    1.37
    Bloom
    1.34
     Blast
    1.33
    Activations Density 0.017%

    No Known Activations