INDEX

Explanations

terms related to accusations and allegations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

InputBorder

-0.58

 tradição

-0.57

@[+][

-0.57

SourceChecksum

-0.56

<?

-0.52

 sahiptir

-0.49

éraire

-0.49

 ciudadana

-0.48

 sostenible

-0.48

 tradizione

-0.48

POSITIVE LOGITS

fx

0.68

 tribal

0.61

 accused

0.60

fx

0.56

accu

0.56

/-/

0.52

FX

0.52

Autoritní

0.50

alleg

0.48

 seized

0.48

Activations Density 0.301%

terms related to accusations and allegations

No Comments

No Known Activations