INDEX

Explanations

phrases related to political accountability and action

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

 Paglinawan

-0.70

 partecipare

-0.63

'{@

-0.55

+#+

-0.54

ímp

-0.52

ourne

-0.48

Décès

-0.46

 parteci

-0.46

INLINE

-0.45

 Boone

-0.45

POSITIVE LOGITS

 relent

0.73

 budge

0.71

 lenker

0.70

 cave

0.69

 wavering

0.66

 capit

0.64

 backed

0.64

 blinked

0.63

 caves

0.61

 hedging

0.60

Activations Density 0.479%

phrases related to political accountability and action

No Comments

No Known Activations