INDEX

Explanations

negations and contractions in conversational language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueGenerated

-0.56

__*/

-0.56

Населення

-0.55

 iprot

-0.54

sizeCache

-0.52

__);

-0.52

erializer

-0.52

 inau

-0.51

 partici

-0.51

esModule

-0.51

POSITIVE LOGITS

ne

0.76

 كومونز

0.74

CppCodeGen

0.65

Viitteet

0.64

endforeach

0.63

]")]

0.60

 ни

0.58

 clearColor

0.58

AnchorStyles

0.58

né

0.57

Activations Density 0.312%

negations and contractions in conversational language

No Comments

No Known Activations