INDEX

Explanations

specific abbreviations or shorthand associated with technical terms and references

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

Abbreviations after initial letters

np_acts-logits-general · gemini-2.0-flash

abbreviations followed by short codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.63

-0.60

la

-0.60

sa

-0.60

op

-0.59

pa

-0.59

er

-0.58

der

-0.58

-0.57

POSITIVE LOGITS

 myſelf

1.25

ſelf

1.19

 raiſ

1.18

 Jefus

1.18

 purpoſe

1.17

 pleaſure

1.17

 Anſ

1.16

 ſever

1.14

 houſe

1.13

 ſmall

1.12

Activations Density 0.427%

specific abbreviations or shorthand associated with technical terms and references

Abbreviations after initial letters

abbreviations followed by short codes

No Comments

No Known Activations