© 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. 9-RES-JB
    11. 14147
    Prev
    Next
    INDEX
    Explanations

    instances of the word "was" followed by single-digit or two-digit numbers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "it was."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ological
    -0.71
    has
    -0.70
     Current
    -0.70
    objects
    -0.70
    onic
    -0.67
    ologically
    -0.66
    continue
    -0.66
    enary
    -0.65
     IMAGES
    -0.64
    allows
    -0.64
    POSITIVE LOGITS
     raining
    1.11
     unclear
    1.10
     inevitable
    0.91
     rumored
    0.88
     obvious
    0.87
     impossible
    0.87
     evident
    0.87
     clear
    0.82
     hoped
    0.82
     easy
    0.80
    Activations Density 0.116%

    No Known Activations