© 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. 4-RES-JB
    11. 573
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating something being not as good or not as strong as something else

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that express ease or difficulty in relation to something

    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
     ACTIONS
    -0.78
     COUR
    -0.68
    olla
    -0.66
     DRAG
    -0.65
    ICA
    -0.65
    âĹ¼
    -0.64
    ardon
    -0.63
    NUM
    -0.63
    DragonMagazine
    -0.62
     Lic
    -0.60
    POSITIVE LOGITS
     anymore
    0.89
     far
    0.89
     nor
    0.85
     well
    0.84
    imilar
    0.83
     much
    0.83
    vernment
    0.81
     evidenced
    0.80
    yet
    0.79
    part
    0.78
    Activations Density 0.073%

    No Known Activations