© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1096
    Prev
    Next
    INDEX
    Explanations

    instances of social interactions and professional relationships in a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships and emotional connections between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isode
    -0.86
    2016
    -0.76
    2015
    -0.74
    gression
    -0.73
     2017
    -0.73
    2017
    -0.72
    atform
    -0.72
    ageddon
    -0.72
    ended
    -0.71
    2014
    -0.71
    POSITIVE LOGITS
     prostitutes
    1.22
     mercenaries
    1.14
     underworld
    1.13
     mafia
    1.13
     thugs
    1.10
     businessmen
    1.10
     mercenary
    1.10
     psychiatrists
    1.06
     shady
    1.04
     KGB
    1.03
    Activations Density 0.912%

    No Known Activations