INDEX

Explanations

terms related to government and military structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 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

RenderAtEndOf

-0.70

insee

-0.65

 nakalista

-0.60

 OMIT

-0.60

__':

-0.58

GenerationType

-0.56

 didat

-0.55

TemporalType

-0.54

getColumnIndex

-0.53

ContentAlignment

-0.53

POSITIVE LOGITS

warf

0.77

 theater

0.73

 kasarigan

0.68

 asymmetric

0.66

 leth

0.66

ISR

0.66

 theatre

0.65

 battlefield

0.64

 theaters

0.64

 littoral

0.63

Activations Density 0.295%

terms related to government and military structures

No Comments

No Known Activations