© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20172
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and agreements

    oai_token-act-pair · gpt-3.5-turbo

    themes related to legal and governmental authority

    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
     Pwr
    -0.49
    hester
    -0.47
     Quote
    -0.46
     Ahead
    -0.46
     fixme
    -0.45
     âĢº
    -0.44
     Shots
    -0.44
    quickShipAvailable
    -0.44
     Sets
    -0.44
    itars
    -0.43
    POSITIVE LOGITS
    ©¶æ
    0.50
    akra
    0.48
    tnc
    0.44
     desired
    0.42
    izoph
    0.41
     lifestyle
    0.41
     predetermined
    0.41
    Recomm
    0.41
     hormone
    0.40
     semblance
    0.40
    Activations Density 5.477%

    No Known Activations