© 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. 10-RES-JB
    11. 11615
    Prev
    Next
    INDEX
    Explanations

    sections related to editing or modifications within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to sections or categories in a structured document

    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
     comprom
    -0.76
    nesday
    -0.71
     lobb
    -0.68
     goose
    -0.66
     baskets
    -0.62
     compliment
    -0.60
     tonight
    -0.60
    racuse
    -0.59
     strateg
    -0.59
     Fug
    -0.58
    POSITIVE LOGITS
     edit
    1.97
     Edit
    1.40
    ?]
    1.25
    edit
    1.21
    ¶
    1.04
     ]
    1.01
    ])
    0.99
    actionDate
    0.94
    src
    0.92
    emphasis
    0.90
    Activations Density 0.016%

    No Known Activations