INDEX

Explanations

keywords related to programming functions and structures

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

ending in "ed"

np_acts-logits-general · gemini-2.0-flash

past tense / participial verbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 houſe

-0.72

 pleaſure

-0.66

 Houſe

-0.59

 ſche

-0.59

 itſelf

-0.59

 purpoſe

-0.58

 ſch

-0.58

ſelf

-0.57

 juges

-0.56

 perſon

-0.56

POSITIVE LOGITS

ized

0.77

ourced

0.77

ted

0.76

ded

0.75

lared

0.74

aced

0.73

iled

0.72

iked

0.71

tered

0.71

ched

0.71

Activations Density 1.095%

keywords related to programming functions and structures

ending in "ed"

past tense / participial verbs

No Comments

No Known Activations