© 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. 6-RES-JB
    11. 15522
    Prev
    Next
    INDEX
    Explanations

    negative words related to behaviors and actions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to morality and ethical behavior

    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
    Bomb
    -0.71
    Joined
    -0.70
    Club
    -0.68
    Legend
    -0.67
    Hug
    -0.65
    Dragon
    -0.65
    rollers
    -0.64
    Alert
    -0.64
     Scream
    -0.63
    Miami
    -0.63
    POSITIVE LOGITS
     empirical
    0.94
     empir
    0.92
     epist
    0.91
     logically
    0.89
     normative
    0.88
     inherent
    0.86
     philosophers
    0.86
     inherently
    0.86
     intrinsically
    0.86
     presupp
    0.85
    Activations Density 1.934%

    No Known Activations