© 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. 19869
    Prev
    Next
    INDEX
    Explanations

    patterns related to code syntax, such as lists and arrays

    oai_token-act-pair · gpt-3.5-turbo

    bracket symbols commonly used in programming or data structures

    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
    wagen
    -0.87
     flown
    -0.74
     occas
    -0.73
     laun
    -0.71
     pens
    -0.69
     plantations
    -0.68
     adolesc
    -0.68
    manship
    -0.67
     extrap
    -0.67
    otted
    -0.67
    POSITIVE LOGITS
    ?]
    1.25
    !]
    1.10
    actionDate
    1.08
    ][
    1.02
    ](
    0.98
    ],
    0.95
    email
    0.91
     ]
    0.91
    âĢ¦]
    0.91
    ].
    0.91
    Activations Density 0.039%

    No Known Activations