© 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. 4-RES-JB
    11. 10696
    Prev
    Next
    INDEX
    Explanations

    complex sequences of characters that likely represent symbols or special characters

    oai_token-act-pair · gpt-3.5-turbo

    references to box office earnings of popular films

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

    No Comments

    Negative Logits
    ".[
    -0.27
    ).[
    -0.24
     Pwr
    -0.22
    .""
    -0.22
    )."
    -0.22
    ]."
    -0.22
    ."[
    -0.22
    }.
    -0.21
    ''.
    -0.20
    )).
    -0.20
    POSITIVE LOGITS
    iaries
    0.22
    ovember
    0.22
    itialized
    0.19
    itzer
    0.19
    earch
    0.19
    viation
    0.18
    uff
    0.18
    eport
    0.18
    ruce
    0.17
    lash
    0.17
    Activations Density 10.509%

    No Known Activations