INDEX

Explanations

references to candidates, particularly in political or formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 invokevirtual

-0.48

 मौ

-0.46

It

-0.45

държа

-0.45

HOL

-0.44

 NSMutable

-0.43

it

-0.43

taur

-0.42

Ho

-0.42

 prefer

-0.42

POSITIVE LOGITS

SequentialGroup

0.87

 utafitiHapana

0.87

WithIOException

0.87

ViewFeatures

0.85

IsContent

0.84

 Composer

0.84

 composers

0.81

tamount

0.80

 AssemblyCulture

0.79

 CANDIDATE

0.78

Activations Density 0.166%

references to candidates, particularly in political or formal contexts

No Comments

No Known Activations