INDEX

Explanations

terms related to "pro," "proactive," and similar prefixes, indicating a focus on positive or forward-thinking actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/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.34.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

ceğine

-0.36

offsetHeight

-0.35

 sorprend

-0.34

olulu

-0.33

noten

-0.31

dispatchEvent

-0.31

ClientSize

-0.30

 elé

-0.30

GenerationType

-0.30

 extrem

-0.29

POSITIVE LOGITS

pro

0.77

Pro

0.71

 صوتيه

0.69

Pro

0.69

pro

0.65

脚注の使い方

0.64

setVerticalGroup

0.59

 prog

0.57

 kasarigan

0.56

 surla

0.53

Activations Density 0.157%

terms related to "pro," "proactive," and similar prefixes, indicating a focus on positive or forward-thinking actions

No Comments

No Known Activations