INDEX

Explanations

terms associated with adjustments, decisions, and evaluations in processes or systems

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

Follows words like "adjustments", "discoveries", "inferences", or "choices"

np_acts-logits-general · gemini-2.0-flash

actions made

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

CodeAttribute

-0.73

setDo

-0.59

jsxFileName

-0.55

 հղումներ

-0.53

complexContent

-0.52

Personendaten

-0.51

 BrowserModule

-0.51

 Longueur

-0.51

 impianti

-0.50

KeyCode

-0.50

POSITIVE LOGITS

 made

1.15

made

0.99

 Made

0.94

 MADE

0.93

Made

0.87

 сделан

0.80

 faits

0.75

making

0.74

MADE

0.73

 feita

0.68

Activations Density 0.590%

terms associated with adjustments, decisions, and evaluations in processes or systems

Follows words like "adjustments", "discoveries", "inferences", or "choices"

actions made

No Comments

No Known Activations