INDEX

Explanations

references to political accusations or investigations related to corruption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Monfieur

-0.79

 Económica

-0.77

 дописавши

-0.73

 Comunicação

-0.68

 Tratado

-0.65

 Embaj

-0.65

ecore

-0.64

 Belén

-0.64

 RIPRODUZIONE

-0.64

 Houſe

-0.61

POSITIVE LOGITS

ThroughAttribute

0.62

BeginContext

0.57

 Italijanski

0.52

writeFieldEnd

0.49

MessageTagHelper

0.49

IN

0.47

Xna

0.47

providedIn

0.47

:+:

0.46

CN

0.45

Activations Density 0.202%

references to political accusations or investigations related to corruption

No Comments

No Known Activations