INDEX

Explanations

strings that indicate types or categories in data representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Radio

-0.49

he

-0.49

 schwer

-0.49

vi

-0.47

ddots

-0.47

<eos>

-0.46

cap

-0.46

')->

-0.45

tru

-0.45

 ام

-0.45

POSITIVE LOGITS

String

1.06

 String

1.03

 raiſ

0.93

STRING

0.92

NSString

0.92

 againſt

0.92

strings

0.88

RegressionTest

0.88

 string

0.86

tring

0.85

Activations Density 0.143%

strings that indicate types or categories in data representation

No Comments

No Known Activations