© 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. 9490
    Prev
    Next
    INDEX
    Explanations

    mention of territories being held by a specific group or faction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to territory controlled by opposition groups

    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
    xxxxxxxx
    -0.61
     traffickers
    -0.59
    Phys
    -0.59
     Express
    -0.59
     impress
    -0.59
    IDENT
    -0.57
     Route
    -0.57
     Typh
    -0.57
    DD
    -0.55
     Reneg
    -0.54
    POSITIVE LOGITS
    held
    1.43
    sburg
    1.10
    scl
    1.04
    erness
    0.96
    theless
    0.94
    quartered
    0.94
    holding
    0.87
    terness
    0.87
    nesday
    0.85
    rontal
    0.85
    Activations Density 0.010%

    No Known Activations