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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1966
    Prev
    Next
    INDEX
    Explanations

    Words related to being impacted or influenced by something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "affected" related to impact on individuals or communities

    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
    YC
    -0.74
    WithNo
    -0.74
    çĦ
    -0.70
    OVA
    -0.70
    True
    -0.68
    outh
    -0.67
    OIL
    -0.67
    ãĤ©
    -0.67
    éĸ
    -0.66
    ALK
    -0.65
    POSITIVE LOGITS
     affected
    1.05
     adversely
    1.00
     effected
    0.98
     impacted
    0.95
     havoc
    0.84
     impact
    0.79
     impacts
    0.78
     negatively
    0.75
     unaffected
    0.73
     Affect
    0.72
    Activations Density 0.020%

    No Known Activations