INDEX

Explanations

phrases related to scientific methodology and data interpretation

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

InstrumentedTest

-0.54

RenderAtEndOf

-0.47

 referenties

-0.47

mpions

-0.46

 customizable

-0.46

 bizi

-0.45

 arbitrar

-0.42

सन्दर्भ

-0.42

 autorytatywna

-0.42

 Políticas

-0.41

POSITIVE LOGITS

nor

0.97

 melainkan

0.77

 anymore

0.70

hoeddwyd

0.68

 nici

0.68

or

0.65

 unless

0.64

اریخ

0.63

Nor

0.61

URLException

0.61

Activations Density 0.810%

phrases related to scientific methodology and data interpretation

No Comments

No Known Activations