INDEX

Explanations

phrases indicating opinions, comparisons, and decision-making contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

enterOuterAlt

-0.41

 capilla

-0.40

sup

-0.36

 deny

-0.35

 intim

-0.34

 theater

-0.34

 dragged

-0.34

 parse

-0.34

 IDENTITY

-0.33

 apologized

-0.33

POSITIVE LOGITS

 zijne

0.60

 GoogleFonts

0.48

)_/¯

0.48

 protoimpl

0.48

endphp

0.46

 actie

0.45

matchCondition

0.44

TabIndex

0.44

 partij

0.44

rethe

0.43

Activations Density 0.628%

phrases indicating opinions, comparisons, and decision-making contexts

No Comments

No Known Activations