INDEX

Explanations

concepts related to the notion of "sense" or understanding in various contexts

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

"sense"

np_acts-logits-general · gemini-2.0-flash

in the sense that

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

GHIJKLM

-0.69

 pleaſure

-0.66

 houſe

-0.66

 WebDriverWait

-0.65

SupportActionBar

-0.62

 Diſ

-0.61

nosotros

-0.61

wira

-0.60

 Saltar

-0.60

 ſtate

-0.60

POSITIVE LOGITS

 tertentu

0.63

MigrationBuilder

0.62

jooq

0.59

 hazır

0.53

AddHtmlAttribute

0.52

of

0.51

Abitanti

0.48

(!__

0.46

kreis

0.45

InitStruct

0.44

Activations Density 0.399%

concepts related to the notion of "sense" or understanding in various contexts

"sense"

in the sense that

No Comments

No Known Activations