INDEX

Explanations

political terms related to obstruction and nominations

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

 Chwiliwch

-0.77

 später

-0.58

 onOptions

-0.58

 JpaRepository

-0.57

argout

-0.56

 بيها

-0.55

uccio

-0.55

onViewCreated

-0.55

 gainera

-0.55

ˈ

-0.54

POSITIVE LOGITS

 again

3.48

again

3.14

Again

3.02

 Again

2.97

 AGAIN

2.88

 once

2.62

 novamente

2.60

 nuevamente

2.56

 nuovamente

2.33

 erneut

2.27

Activations Density 1.029%

political terms related to obstruction and nominations

No Comments

No Known Activations