© 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. 1-RES-JB
    11. 7242
    Prev
    Next
    INDEX
    Explanations

    phrases related to disagreement or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "entertainment" or "entertainment-related terms."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.84
    BILITIES
    -0.80
    ackets
    -0.72
    phrine
    -0.69
    STER
    -0.69
    estyles
    -0.65
     Kills
    -0.64
    axter
    -0.63
    ãģ®éŃĶ
    -0.63
     Supports
    -0.61
    POSITIVE LOGITS
    ent
    1.18
    ence
    0.93
    ropy
    0.92
    reprene
    0.91
    inel
    0.85
    ents
    0.84
    ertain
    0.84
    ral
    0.84
    ented
    0.79
    acles
    0.79
    Activations Density 0.019%

    No Known Activations