© 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. 4-RES-JB
    11. 635
    Prev
    Next
    INDEX
    Explanations

    transitions indicating an alternative course of action or decision

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an alternative or substitution

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

    No Comments

    Negative Logits
     neighbourhood
    -0.74
    vez
    -0.67
    SAN
    -0.62
    cision
    -0.61
    ASED
    -0.61
     MIL
    -0.61
     foundations
    -0.60
     derby
    -0.60
    rament
    -0.60
    aph
    -0.60
    POSITIVE LOGITS
     instead
    0.74
     opting
    0.72
    ctr
    0.72
    replace
    0.69
    ĩ
    0.65
    Instead
    0.65
    IJ
    0.64
    oppers
    0.64
     Instead
    0.64
    Ļ½
    0.64
    Activations Density 0.017%

    No Known Activations