INDEX

Explanations

terms related to initial conditions or values in various contexts

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

Follows the word "initial"

np_acts-logits-general · gemini-2.0-flash

initial state or condition

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

</i>

-0.66

</b>

-0.61

Borg

-0.57

hra

-0.56

vo

-0.56

ى

-0.56

po

-0.54

xFE

-0.54

Fox

-0.53

נד

-0.53

POSITIVE LOGITS

 pleaſure

1.14

 purpoſe

1.07

ſelves

0.93

Cyfeiriadau

0.92

 itſelf

0.92

 téléphonique

0.91

 myſelf

0.91

contentLoaded

0.90

 Inti

0.90

aarrggbb

0.89

Activations Density 0.155%

terms related to initial conditions or values in various contexts

Follows the word "initial"

initial state or condition

No Comments

No Known Activations