INDEX

Explanations

phrases related to searching for specific items or information

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

Following "for" in programming/searching contexts

np_acts-logits-general · gemini-2.0-flash

looking for signs

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

 itſelf

-0.81

EDEFAULT

-0.81

 raiſ

-0.80

MigrationBuilder

-0.77

LabelTagHelper

-0.73

AccessorTable

-0.70

extAlignment

-0.70

 AttributeSet

-0.69

 springfox

-0.68

 FBref

-0.67

POSITIVE LOGITS

 clues

0.74

 signs

0.56

 глазами

0.52

 cues

0.52

 signes

0.51

bilecek

0.48

 keberadaan

0.47

gelijke

0.45

 presença

0.45

any

0.45

Activations Density 0.225%

phrases related to searching for specific items or information

Following "for" in programming/searching contexts

looking for signs

No Comments

No Known Activations