INDEX

Explanations

occurrences of organizational and library references in code or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 <<<<<<<<<<<<<<

-0.93

EndContext

-0.90

 Bourgoin

-0.77

SharedCtor

-0.75

 itſelf

-0.73

 schme

-0.72

ьаж

-0.71

twimg

-0.71

HtmlAttribute

-0.71

 Wikimedijinoj

-0.69

POSITIVE LOGITS

edu

0.82

com

0.78

edu

0.73

gov

0.64

ttps

0.54

pring

0.52

javax

0.51

GOV

0.48

scher

0.47

 paroi

0.47

Activations Density 0.051%

occurrences of organizational and library references in code or documentation

No Comments

No Known Activations