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

    Neuronpedia

    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. 10-RES-JB
    11. 8238
    Prev
    Next
    INDEX
    Explanations

    sentences containing instructions or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to crime and social behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     witnessing
    -0.75
    IDER
    -0.67
    atform
    -0.65
    BuyableInstoreAndOnline
    -0.65
     contemplated
    -0.62
    ģĸ
    -0.62
     understatement
    -0.61
    CONCLUS
    -0.61
     Examination
    -0.59
     attempted
    -0.58
    POSITIVE LOGITS
     everybody
    1.12
     blah
    1.07
     dudes
    1.06
     fuckin
    1.04
    they
    1.02
     guys
    1.02
     shit
    1.02
     crap
    1.00
     stuff
    1.00
     anyways
    1.00
    Activations Density 0.695%

    No Known Activations