© 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. 2-RES-JB
    11. 1464
    Prev
    Next
    INDEX
    Explanations

    the word "God" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "od."

    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
     Ago
    -0.74
     Citadel
    -0.64
     silence
    -0.61
     shorth
    -0.61
    âĸ¬
    -0.60
     Quit
    -0.59
     Tempest
    -0.58
     Goat
    -0.58
     Jihad
    -0.57
     mu
    -0.57
    POSITIVE LOGITS
    yssey
    1.15
    od
    1.13
    sworth
    1.12
    opter
    1.10
    odon
    1.09
    iamond
    1.08
    unn
    1.03
    amn
    1.00
    ont
    0.99
    ata
    0.99
    Activations Density 0.012%

    No Known Activations