INDEX

Explanations

code and configuration-related terms associated with files and directories

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

File paths or directories

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

StructEnd

-0.52

RTEE

-0.40

EditorBrowsable

-0.40

 MainAxisSize

-0.40

ValueStyle

-0.36

utilisons

-0.35

 Breaking

-0.34

 للاسماء

-0.33

ISupport

-0.33

 whome

-0.33

POSITIVE LOGITS

 path

1.47

 Path

1.23

 paths

1.22

path

1.20

Path

1.16

 Paths

1.13

路径

1.09

 pathway

1.02

Paths

0.98

 PATH

0.98

Activations Density 0.300%

code and configuration-related terms associated with files and directories

File paths or directories

No Comments

No Known Activations