INDEX

Explanations

references to examples and instances

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

"for" followed by "example" or "instance"

np_acts-logits-general · gemini-2.0-flash

for example

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 such

-0.72

such

-0.71

Such

-0.69

 Such

-0.65

 таких

-0.59

 SUCH

-0.57

 такие

-0.56

 tels

-0.55

 telles

-0.54

 solche

-0.53

POSITIVE LOGITS

 example

1.68

 instance

1.31

 EXAMPLE

1.23

 Example

1.17

example

1.16

 exemplo

1.13

Example

1.10

 exemple

1.08

 ejemplo

1.07

AddTagHelper

1.02

Activations Density 0.144%

references to examples and instances

"for" followed by "example" or "instance"

for example

No Comments

No Known Activations