INDEX

Explanations

instances of the word "symbol" and its variations in the context of definitions and references

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

เภ

-0.78

WriteAttribute

-0.68

sizeCache

-0.66

floxacin

-0.66

 Garry

-0.62

$[-

-0.61

 Gilli

-0.61

Décès

-0.59

RunWith

-0.59

devamını

-0.59

POSITIVE LOGITS

 symbols

2.45

 symbol

2.37

 Symbols

2.25

 Symbol

2.24

 SYMBOL

2.24

symbol

2.19

symbols

2.17

Symbols

2.16

SYMBOL

2.10

Symbol

2.08

Activations Density 0.045%

instances of the word "symbol" and its variations in the context of definitions and references

No Comments

No Known Activations