INDEX

Explanations

punctuation and special characters

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

Tokens appearing inside parentheses or after commas

np_acts-logits-general · gemini-2.0-flash

conjunctions and separators

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.01

 myſelf

-0.96

 houſe

-0.92

 ſmall

-0.92

 Monfieur

-0.92

 purpoſe

-0.92

 ſeveral

-0.91

 pleaſure

-0.89

 greateſt

-0.88

 ſche

-0.86

POSITIVE LOGITS

and

1.14

 plus

0.96

or

0.84

以及

0.81

0.78

plus

0.76

 sowie

0.74

0.72

and

0.71

 also

0.70

Activations Density 0.762%

punctuation and special characters

Tokens appearing inside parentheses or after commas

conjunctions and separators

No Comments

No Known Activations