© 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. 2-RES-JB
    11. 12744
    Prev
    Next
    INDEX
    Explanations

    sequences enclosed in square brackets that are likely snippets of larger text

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or omissions, often indicating pauses or missing context within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cradle
    -0.74
    amins
    -0.73
    osaurs
    -0.66
    imens
    -0.66
    aeus
    -0.65
     anniversary
    -0.64
    grass
    -0.64
    ops
    -0.64
    onite
    -0.62
     anx
    -0.62
    POSITIVE LOGITS
    ...]
    1.01
    CLASSIFIED
    0.93
     [...]
    0.93
    âĢ¦]
    0.88
    Bloomberg
    0.85
    VERTISEMENT
    0.84
    },{"
    0.82
     Appears
    0.82
     ],
    0.78
    REDACTED
    0.76
    Activations Density 0.022%

    No Known Activations