© 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. 11-RES-JB
    11. 6845
    Prev
    Next
    INDEX
    Explanations

    descriptions of technical components or features

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize completeness or the inclusion of all necessary elements

    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
    nesday
    -0.80
    imity
    -0.73
    Interstitial
    -0.69
    cause
    -0.68
    icker
    -0.68
    taboola
    -0.68
     )]
    -0.67
    eme
    -0.66
    eeper
    -0.64
    laugh
    -0.63
    POSITIVE LOGITS
     needed
    1.15
     imaginable
    1.11
     necessary
    1.07
     required
    0.98
     essentials
    0.96
     except
    0.94
     requisite
    0.94
    needed
    0.91
     plus
    0.90
     minus
    0.84
    Activations Density 0.262%

    No Known Activations