INDEX

Explanations

specific numeric identifiers or codes, particularly in the context of technical documentation or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

CrossRef

-0.64

bewerken

-0.61

ValueStyle

-0.61

})();

-0.59

errHandler

-0.59

 дописавши

-0.59

IsMutable

-0.57

RenderAtEndOf

-0.56

PhysRevLett

-0.55

 Walkover

-0.55

POSITIVE LOGITS

 Brist

0.51

bitat

0.48

IndentedString

0.47

Jac

0.43

toxin

0.43

queness

0.43

siella

0.42

adamia

0.41

ledge

0.40

 bary

0.40

Activations Density 0.401%

specific numeric identifiers or codes, particularly in the context of technical documentation or programming

No Comments

No Known Activations