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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 10245
    Prev
    Next
    INDEX
    Explanations

    instances where something is being done in place of another option

    oai_token-act-pair · gpt-3.5-turbo

    the word "instead" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andestine
    -0.69
    ankind
    -0.66
    ESE
    -0.61
     Shake
    -0.61
    IENT
    -0.61
    vez
    -0.59
    ced
    -0.58
     Smash
    -0.56
    iky
    -0.56
    orsi
    -0.55
    POSITIVE LOGITS
     opting
    0.86
     thereof
    0.80
    paces
    0.73
     opt
    0.70
     preferring
    0.69
    ocus
    0.69
     relying
    0.67
     than
    0.67
    liga
    0.66
    uristic
    0.65
    Activations Density 0.023%

    No Known Activations