© 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. 17074
    Prev
    Next
    INDEX
    Explanations

    phrases related to solving problems or developing strategies

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progress or outcomes

    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
     Mour
    -0.69
     suscept
    -0.68
     Deaths
    -0.67
    llah
    -0.65
    desc
    -0.65
    ANCE
    -0.64
     effected
    -0.64
     Ambro
    -0.61
    must
    -0.60
    heading
    -0.60
    POSITIVE LOGITS
    bler
    0.69
    ipeg
    0.68
    ictionary
    0.67
    agra
    0.65
     diligently
    0.65
    pause
    0.65
    strate
    0.63
     prostitutes
    0.62
    emouth
    0.62
     earnest
    0.62
    Activations Density 0.822%

    No Known Activations