INDEX

Explanations

occurrences of the word "sign" and its variations, indicating actions related to agreements or contracts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 jsPsych

-0.54

ynb

-0.54

SpringBootTest

-0.53

chtet

-0.50

Халык

-0.49

脚注の使い方

-0.48

 TType

-0.47

CURLOPT

-0.47

 Marat

-0.47

CppMethod

-0.47

POSITIVE LOGITS

 Sign

0.87

 sign

0.84

 Signing

0.80

Sign

0.79

 signing

0.79

Signing

0.76

 SIGN

0.74

 signed

0.71

sign

0.69

SIGN

0.66

Activations Density 0.117%

occurrences of the word "sign" and its variations, indicating actions related to agreements or contracts

No Comments

No Known Activations