INDEX

Explanations

references to conflicts or disagreements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 velkommen

-0.69

GraphicsUnit

-0.58

verständlich

-0.54

 dangereux

-0.52

 klart

-0.49

adpleegd

-0.49

matig

-0.49

 cref

-0.48

SharedDtor

-0.48

MessageState

-0.48

POSITIVE LOGITS

]=='

0.64

tvguidetime

0.60

jetunion

0.56

 estekak

0.56

migrationBuilder

0.56

).__

0.55

NavController

0.55

Atsauces

0.54

'>"

0.53

 RSSSF

0.53

Activations Density 0.816%

references to conflicts or disagreements in various contexts

No Comments

No Known Activations