© 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. 2-RES-JB
    11. 3260
    Prev
    Next
    INDEX
    Explanations

    phrases related to queries or commands

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about the nature of processes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isher
    -0.67
     Goth
    -0.60
    agonists
    -0.58
     Guer
    -0.56
    uthor
    -0.54
    ception
    -0.54
    agonist
    -0.54
     )]
    -0.53
    lehem
    -0.53
    ãĤ«
    -0.53
    POSITIVE LOGITS
    soever
    0.96
    ever
    0.81
    HCR
    0.80
    ls
    0.79
    ling
    0.75
     MUCH
    0.75
    beit
    0.73
     much
    0.73
     exactly
    0.70
    much
    0.70
    Activations Density 0.066%

    No Known Activations