INDEX

Explanations

relationships or connections between concepts and their context

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

Followed by "of", "a", or "the"

np_acts-logits-general · gemini-2.0-flash

special characters and abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

++.

-0.77

-0.65

 autorytatywna

-0.63

。

-0.62

।

-0.60

".

-0.59

-0.58

%.

-0.56

'.

-0.56

.\\

-0.56

POSITIVE LOGITS

 these

0.80

seamnă

0.78

 AssemblyCompany

0.75

 چنین

0.73

서는

0.72

 such

0.72

 BoxDecoration

0.72

 solch

0.70

 solches

0.70

 δὲ

0.69

Activations Density 1.063%

relationships or connections between concepts and their context

Followed by "of", "a", or "the"

special characters and abbreviations

No Comments

No Known Activations