© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 2579
    Prev
    Next
    INDEX
    Explanations

    structured data patterns with text in a specific format, such as historical references with editing tags

    oai_token-act-pair · gpt-3.5-turbo

    bracketed notations and references, often indicating sections or footnotes in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.74
     redu
    -0.70
     seams
    -0.68
     rooft
    -0.67
    mable
    -0.67
     scraps
    -0.64
     thous
    -0.64
     surrogate
    -0.64
     Elys
    -0.64
     equivalents
    -0.63
    POSITIVE LOGITS
    ?]
    1.38
     edit
    1.36
    Pg
    1.05
    !]
    1.05
    ËĪ
    1.04
    :]
    1.02
    ...]
    1.01
     ]
    1.00
     ][
    0.96
    actionDate
    0.94
    Activations Density 0.025%

    No Known Activations