INDEX

Explanations

references to popular culture and social commentary

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Whilst

-1.14

Whilst

-1.14

 utilising

-0.93

 poichè

-0.91

 whilst

-0.88

 utilise

-0.83

favourable

-0.80

 endeavour

-0.79

 endeavours

-0.79

hésite

-0.78

POSITIVE LOGITS

 pols

0.77

ain

0.73

bof

0.67

 herewith

0.66

 lousy

0.66

 darn

0.66

 …)

0.66

gee

0.65

 ...)

0.64

sez

0.63

Activations Density 0.901%

references to popular culture and social commentary

No Comments

No Known Activations