© 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. 0-RES-JB
    11. 8269
    Prev
    Next
    INDEX
    Explanations

    references to things that have been changed or modified

    oai_token-act-pair · gpt-3.5-turbo

    references to changes or modifications

    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
     Qualcomm
    -0.73
    queue
    -0.69
    Phone
    -0.69
    CTV
    -0.67
    gi
    -0.65
    ppo
    -0.65
    tu
    -0.65
    minimum
    -0.64
    ku
    -0.64
    coal
    -0.64
    POSITIVE LOGITS
     altered
    3.16
     alteration
    2.66
     alterations
    2.58
     altering
    2.43
     alters
    2.32
     alter
    2.18
    alter
    1.73
     Alter
    1.62
     modification
    1.48
     modifications
    1.42
    Activations Density 0.019%

    No Known Activations