INDEX

Explanations

phrases that indicate a basis for arguments or statements

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

"based"

np_acts-logits-general · gemini-2.0-flash

based on

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

ViewChild

-0.66

StringWriter

-0.56

Jeografia

-0.56

handleError

-0.55

 nocturne

-0.54

ἁ

-0.54

ి

-0.53

 Drapeau

-0.52

 Ginn

-0.52

 caoutchouc

-0.51

POSITIVE LOGITS

Based

1.13

BASED

1.12

 Based

1.12

 based

1.07

 BASED

1.06

 basé

1.04

based

1.00

 basée

0.95

 basado

0.84

に基

0.83

Activations Density 0.119%

phrases that indicate a basis for arguments or statements

"based"

based on

No Comments

No Known Activations