INDEX

Explanations

keywords or phrases related to information and data processing

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

Prefixes: dif-, com-, pro-, ac-, sig-, permis-

np_acts-logits-general · gemini-2.0-flash

prefix patterns like dif- com- pro- hun- ac- permis- signifi-

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

ſelf

-1.07

wiſe

-1.00

neſs

-0.99

 Majefty

-0.97

NUMX

-0.97

 itſelf

-0.94

 myſelf

-0.94

ſelves

-0.91

enumii

-0.90

eſt

-0.90

POSITIVE LOGITS

0.75

∣

0.64

↵

0.62

-,

0.61

↵↵

0.58

-.

0.57

<eos>

0.54

0.53

 independencia

0.53

¬

0.51

Activations Density 0.248%

keywords or phrases related to information and data processing

Prefixes: dif-, com-, pro-, ac-, sig-, permis-

prefix patterns like dif- com- pro- hun- ac- permis- signifi-

No Comments

No Known Activations