© 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. 11-RES-JB
    6. 22680
    Prev
    Next
    INDEX
    Explanations

    descriptions of groups of individuals

    oai_token-act-pair · gpt-3.5-turbo

    narratives involving groups of characters, particularly female leads and their interpersonal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ])
    -0.86
     ))
    -0.84
    ]).
    -0.83
    ])
    -0.81
    statement
    -0.77
    )))
    -0.75
    Ô
    -0.73
     GOODMAN
    -0.71
     Statements
    -0.71
    "))
    -0.70
    POSITIVE LOGITS
     discovers
    1.09
     kidnapped
    1.01
     haunted
    0.99
     stranded
    0.99
     embark
    0.98
     journeys
    0.97
     unwittingly
    0.96
     adventures
    0.95
     mysteriously
    0.93
     pursued
    0.93
    Activations Density 0.391%

    No Known Activations