© 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. 8-RES-JB
    11. 4200
    Prev
    Next
    INDEX
    Explanations

    information related to personal and professional backgrounds of individuals

    oai_token-act-pair · gpt-3.5-turbo

    entities and roles related to professional and organizational positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sudden
    -0.68
     spontaneous
    -0.67
     rushed
    -0.66
     unexpected
    -0.64
     brut
    -0.60
     THEN
    -0.59
     reveal
    -0.59
     catastrophic
    -0.59
     abrupt
    -0.59
     destruct
    -0.59
    POSITIVE LOGITS
     whereas
    0.77
     oversees
    0.74
     owns
    0.72
    ;;;;
    0.68
    ;;;;;;;;;;;;
    0.65
    adj
    0.65
     affiliate
    0.64
    formerly
    0.64
     lia
    0.62
    .)
    0.62
    Activations Density 1.041%

    No Known Activations