© 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. 9040
    Prev
    Next
    INDEX
    Explanations

    phrases indicating successful outcomes or achievements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "successfully"

    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
     Ancients
    -0.68
     Warcraft
    -0.68
     Rober
    -0.66
     newsletters
    -0.65
     Relief
    -0.64
     Origin
    -0.63
    Orig
    -0.61
    Eth
    -0.61
     Flames
    -0.61
     anonymity
    -0.59
    POSITIVE LOGITS
     succeed
    0.89
     reproduce
    0.88
     successfully
    0.85
     destro
    0.83
     navig
    0.82
     achieved
    0.81
     competed
    0.78
     mastered
    0.77
     exting
    0.76
    TAIN
    0.76
    Activations Density 0.005%

    No Known Activations