© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 1627
    Prev
    Next
    INDEX
    Explanations

    phrases indicating logical conclusions

    oai_token-act-pair · gpt-3.5-turbo

    the word "therefore" and related logical connectors

    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
     Feld
    -0.76
     Demons
    -0.67
     Defenders
    -0.65
    ¢
    -0.62
     Nurs
    -0.61
    ten
    -0.61
     Wall
    -0.59
    ender
    -0.59
    DL
    -0.58
     Freddy
    -0.58
    POSITIVE LOGITS
    forth
    0.99
    ĵĺ
    0.84
    ħĭ
    0.83
    rehend
    0.83
     necess
    0.81
     guiActiveUn
    0.80
     ingred
    0.80
    ettings
    0.79
     dilig
    0.76
    uracy
    0.75
    Activations Density 0.016%

    No Known Activations