INDEX

Explanations

references to the term "Shi" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Tind

-0.60

translates

-0.59

fileID

-0.58

 rootView

-0.58

 مصرى

-0.58



-0.57

 editados

-0.56

Tembelea

-0.56

 Quint

-0.55

Rhy

-0.55

POSITIVE LOGITS

 Celebrity

0.90

 celebrity

0.86

Shi

0.83

Celebrity

0.79

 actors

0.79

 celebrities

0.76

Shi

0.76

actors

0.74

 actor

0.74

ReusableCell

0.74

Activations Density 0.073%

references to the term "Shi" in various contexts

No Comments

No Known Activations