© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    6. 6566
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and announcements

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and announcements related to electronic devices and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mour
    -0.66
     funer
    -0.64
     prayed
    -0.64
    nat
    -0.62
     poems
    -0.62
    yll
    -0.60
    ghazi
    -0.60
     Cous
    -0.59
     inflicted
    -0.59
     deport
    -0.59
    POSITIVE LOGITS
     Huawei
    0.90
     Xiaomi
    0.87
    Samsung
    0.85
     Lenovo
    0.82
     HTC
    0.82
     IoT
    0.80
     Samsung
    0.80
     OEM
    0.80
    atform
    0.79
     SDK
    0.79
    Activations Density 3.562%

    No Known Activations