INDEX

Explanations

elements related to instructions or steps in a process

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

Prefers certain words or phrases

np_acts-logits-general · gemini-2.0-flash

alternatives or preferences

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

AutoScaleMode

-0.59

stateProvider

-0.57

SpringRunner

-0.55

KEYCODE

-0.53

UserScript

-0.51

 dagegen

-0.51

HttpPut

-0.51

=?

-0.50

RUnlock

-0.49

reszcie

-0.49

POSITIVE LOGITS

 preferably

1.39

 ideally

1.25

 Preferably

1.21

preferably

1.18

 Ideally

1.12

Ideally

1.09

Prefer

1.06

 preferable

0.98

最好

0.95

 preferred

0.92

Activations Density 0.447%

elements related to instructions or steps in a process

Prefers certain words or phrases

alternatives or preferences

No Comments

No Known Activations