INDEX

Explanations

symbols and punctuation marks, particularly exclamations and questions

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

inį

-0.60

maketitle

-0.59

jai

-0.57

ganj

-0.56

 Shuk

-0.55

funcion

-0.55

 suitable

-0.53

wol

-0.53

 bora

-0.52

uanya

-0.52

POSITIVE LOGITS

 <=",

1.19

 AssemblyCulture

0.95

MigrationBuilder

0.92

“…”

0.92

الإنجليزية

0.91

“……”

0.88

 propOrder

0.87

 '\\;'

0.87

IsContent

0.86

AndEndTag

0.86

Activations Density 0.072%

symbols and punctuation marks, particularly exclamations and questions

No Comments

No Known Activations