© 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
    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. 22384
    Prev
    Next
    INDEX
    Explanations

    mentions or references to various types of models, such as sustainable business models, female role models, and economic models

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of models

    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
    rib
    -0.71
    orate
    -0.71
    odium
    -0.68
     incre
    -0.65
    adelphia
    -0.64
    chip
    -0.63
    icket
    -0.63
    opa
    -0.63
     foul
    -0.62
     Glen
    -0.62
    POSITIVE LOGITS
     models
    3.87
     Models
    3.19
    models
    2.88
     model
    2.82
    model
    2.44
    Model
    2.19
     modeling
    2.14
     Model
    2.13
     modelling
    2.05
     modeled
    1.55
    Activations Density 0.010%

    No Known Activations