INDEX

Explanations

words related to table structures or attributes, particularly in the context of data organization

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

words ending in able or ible

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ing

-0.85

-0.83

es

-0.72

-0.71

-0.60

-0.59

jspx

-0.58

en

-0.57

POSITIVE LOGITS

Efq

1.06

izable

1.06

ABLE

1.05

gable

1.05

chable

1.03

ourable

1.02

 Theſe

1.02

vable

1.02

^(@)

1.02

 ་་

1.01

Activations Density 0.147%

words related to table structures or attributes, particularly in the context of data organization

words ending in able or ible

No Comments

No Known Activations