© 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. 3-RES-JB
    11. 3438
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "upside."

    oai_token-act-pair · gpt-3.5-turbo

    references to potential benefits or positive attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®éŃĶ
    -0.96
    ãģ®å®
    -0.83
    naire
    -0.81
    ocal
    -0.77
    ocally
    -0.76
    tein
    -0.74
    nance
    -0.71
    ions
    -0.70
    Rush
    -0.69
    sonian
    -0.69
    POSITIVE LOGITS
     upside
    1.33
     srfAttach
    0.90
     blind
    0.76
    olicy
    0.76
    ï¸
    0.70
     facing
    0.69
    vable
    0.68
     ceiling
    0.68
     handc
    0.67
     heel
    0.67
    Activations Density 0.008%

    No Known Activations