INDEX

Explanations

words that express inclusivity or commonly reference groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ThroughAttribute

-0.76

LabelTagHelper

-0.76

TagMode

-0.70

 propOrder

-0.70

 réguli

-0.67

 greateſt

-0.67

ystema

-0.64

 Cedric

-0.64

 noires

-0.61

 Theſe

-0.61

POSITIVE LOGITS

 đều

0.83

 nhau

0.58

 very

0.56

bajo

0.56

enumi

0.56

 being

0.55

 were

0.54

very

0.54

tocin

0.53

urti

0.52

Activations Density 0.199%

words that express inclusivity or commonly reference groups

No Comments

No Known Activations