© 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. 6-RES-JB
    11. 17729
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions with significant impact and consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulatory policies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tud
    -0.64
     Kardash
    -0.62
    aer
    -0.62
     Vers
    -0.61
     Roose
    -0.61
     didnt
    -0.61
     Benn
    -0.60
     Aer
    -0.59
     Awakens
    -0.59
     Dunk
    -0.56
    POSITIVE LOGITS
    onite
    0.77
    lie
    0.70
    senal
    0.69
    combe
    0.68
    etheless
    0.68
    Ļ½
    0.66
    osate
    0.66
    -+
    0.65
    JECT
    0.65
    ifully
    0.64
    Activations Density 1.263%

    No Known Activations