© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 399
    Prev
    Next
    INDEX
    Explanations

    conclusions or implications based on given information

    oai_token-act-pair · gpt-3.5-turbo

    the word "therefore" indicating logical conclusions or reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Defenders
    -0.69
    Fram
    -0.66
     Feld
    -0.64
     Debor
    -0.63
     Yel
    -0.63
     Patty
    -0.62
     Franklin
    -0.62
    MM
    -0.61
     Ott
    -0.60
     Vancouver
    -0.60
    POSITIVE LOGITS
    forth
    1.16
    ettings
    0.84
    uracy
    0.82
     facto
    0.79
    elist
    0.78
     guiActiveUn
    0.77
    ãģ®éŃĶ
    0.76
     necess
    0.76
     theoretically
    0.75
    odynam
    0.74
    Activations Density 0.020%

    No Known Activations