© 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. 1-RES-JB
    11. 8914
    Prev
    Next
    INDEX
    Explanations

    phrases related to transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "change," particularly in the context of societal, environmental, or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.93
    RAY
    -0.84
    ¯¯¯¯
    -0.84
    è»
    -0.82
    è£ħ
    -0.82
    ãĥĦ
    -0.80
    APH
    -0.80
    çĦ
    -0.80
    ç«
    -0.75
    è¡
    -0.74
    POSITIVE LOGITS
     Change
    0.99
    imedia
    0.75
     Catalyst
    0.75
     Consent
    0.73
    nces
    0.73
     Hands
    0.72
     Bind
    0.70
     Bride
    0.70
     Cause
    0.69
     Trends
    0.69
    Activations Density 0.014%

    No Known Activations