© 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. 21030
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or entities, possibly related to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations and brands, particularly in relation to events or entities associated with them

    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
    ivities
    -0.83
    RED
    -0.80
    verted
    -0.78
    rup
    -0.78
    ndra
    -0.75
    ends
    -0.75
    nings
    -0.71
    Pope
    -0.71
    nen
    -0.70
    ributed
    -0.70
    POSITIVE LOGITS
     Maz
    0.90
    urat
    0.69
     slate
    0.67
    ombies
    0.66
     Jaw
    0.65
     assum
    0.65
    illary
    0.65
    ushima
    0.65
    è¦ļéĨĴ
    0.64
    uppet
    0.64
    Activations Density 0.017%

    No Known Activations