INDEX

Explanations

references to the study or paper being discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 itſelf

-0.82

)++;

-0.79

 للاسماء

-0.75

 myſelf

-0.74

 '\\;'

-0.71

++)

-0.71

 ſeveral

-0.70

 themſelves

-0.69

Eſ

-0.67

ſelf

-0.67

POSITIVE LOGITS

 paper

1.43

paper

1.06

 report

0.96

 Paper

0.91

Paper

0.89

 article

0.87

 PAPER

0.79

 thesis

0.74

 study

0.71

PAPER

0.70

Activations Density 0.388%

references to the study or paper being discussed

No Comments

No Known Activations