INDEX

Explanations

terms related to scientific classifications or terminologies, particularly in biology and genetics

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

ending in "er", "or", "ic", "al"

np_acts-logits-general · gemini-2.0-flash

word endings and suffixes

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

 CommonModule

-0.73

nitus

-0.72

tonode

-0.66

didSet

-0.66

السكان

-0.63

pretty

-0.60

skraft

-0.60

ciutto

-0.60

httphttps

-0.60

survi

-0.59

POSITIVE LOGITS

er

1.04

ER

0.69

enumi

0.67

theless

0.65

rungsseite

0.63

gonic

0.62

IOR

0.61

iver

0.60

ior

0.58

RRRR

0.57

Activations Density 0.370%

terms related to scientific classifications or terminologies, particularly in biology and genetics

ending in "er", "or", "ic", "al"

word endings and suffixes

No Comments

No Known Activations