© 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. 0-RES-JB
    11. 4223
    Prev
    Next
    INDEX
    Explanations

    keywords related to opportunities or opposition

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "opposition" or "opportunistic" themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     burns
    -0.68
     metal
    -0.67
     synthetic
    -0.60
     concerning
    -0.59
     Euro
    -0.58
     grade
    -0.58
     factor
    -0.58
     note
    -0.58
     gamma
    -0.57
     Wales
    -0.57
    POSITIVE LOGITS
    opp
    4.49
    Opp
    1.96
     Opp
    1.44
     opp
    1.27
    opped
    1.24
    oppy
    1.23
    oppers
    1.20
    advant
    1.12
    opping
    1.07
     opposition
    1.06
    Activations Density 0.005%

    No Known Activations