INDEX

Explanations

references to citations and academic research formats

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 yourselves

-0.83

 collectively

-0.81

 themselves

-0.69

 <>",

-0.67

 ourselves

-0.65

thyst

-0.65

eds

-0.64

 elkaar

-0.64

 together

-0.64

 collective

-0.62

POSITIVE LOGITS

 solo

0.73

 single

0.63

 sola

0.62

single

0.61

 lone

0.61

一人で

0.59

 lonely

0.59

alone

0.58

 sozinho

0.58

Alone

0.57

Activations Density 0.454%

references to citations and academic research formats

No Comments

No Known Activations