© 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. 4-RES-JB
    11. 4832
    Prev
    Next
    INDEX
    Explanations

    words related to making a significant impact or change

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of making an impact or contribution

    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
    Grey
    -0.74
     Gemini
    -0.69
    çĦ
    -0.69
    OAD
    -0.65
     ACTIONS
    -0.65
    Optional
    -0.64
     Creed
    -0.63
    MQ
    -0.63
     Cambodia
    -0.63
     Gathering
    -0.63
    POSITIVE LOGITS
     dent
    1.22
    istry
    1.13
    inas
    1.01
    orial
    0.97
    icles
    0.97
    rition
    0.91
    ricular
    0.90
    ures
    0.89
    ysis
    0.89
    icer
    0.86
    Activations Density 0.004%

    No Known Activations