INDEX

Explanations

conditional phrases that indicate hypothetical situations

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

Followed by conditional statements

np_acts-logits-general · gemini-2.0-flash

if followed by pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 ―――――

-0.93

 photolibrary

-0.74

 ་་

-0.73

 vectorstock

-0.72

ſelf

-0.70

 tfsi

-0.70

SPS

-0.69

 uchiha

-0.69

 cdti

-0.69

 itſelf

-0.68

POSITIVE LOGITS

it

1.11

you

1.10

if

1.02

 they

1.01

If

0.98

 indeed

0.94

 there

0.91

we

0.87

IF

0.85

 this

0.84

Activations Density 0.163%

conditional phrases that indicate hypothetical situations

Followed by conditional statements

if followed by pronouns

No Comments

No Known Activations