INDEX

Explanations

repetitive structures in text referring to variables and relationships

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

references or footnotes

np_acts-logits-general · gemini-2.0-flash

referencing preceding text or notes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

::::::::

-0.59

SharedCtor

-0.59

Hentet

-0.49

原始内容存档于

-0.47

InjectAttribute

-0.47

 Roskov

-0.45

Indeed

-0.45

 CreateTagHelper

-0.43

indeed

-0.43

ftagPool

-0.41

POSITIVE LOGITS

 above

1.11

 précédente

0.96

 acima

0.92

above

0.91

 précédent

0.84

上面的

0.80

 précédentes

0.78

 previous

0.78

 précédents

0.78

bove

0.77

Activations Density 0.456%

repetitive structures in text referring to variables and relationships

references or footnotes

referencing preceding text or notes

No Comments

No Known Activations