INDEX

Explanations

mentions of alcohol and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 createSprite

-0.79

seamnă

-0.69

GTS

-0.66

\":\"

-0.64

zag

-0.64

:=\

-0.64

Ӕ

-0.64

 Carrington

-0.64

嘧

-0.63

]-->

-0.63

POSITIVE LOGITS

 alcohol

2.00

 Alcohol

1.90

alcohol

1.88

Alcohol

1.84

 ALCOHOL

1.82

 alcohols

1.59

COHOL

1.55

 Alkohol

1.42

 alkohol

1.37

Alco

1.29

Activations Density 0.069%

mentions of alcohol and related terms

No Comments

No Known Activations