INDEX

Explanations

conditional phrases that introduce hypothetical situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 reise

-0.71

 Breslau

-0.66

PLA

-0.64

PLA

-0.63

edu

-0.62

 Brust

-0.62

meiras

-0.61

 Cooley

-0.61

OIR

-0.60

CLO

-0.60

POSITIVE LOGITS

if

1.76

If

1.45

if

1.40

checkIf

1.32

IF

1.30

If

1.30

Nếu

1.26

 hvis

1.24

 jika

1.24

หาก

1.23

Activations Density 0.197%

conditional phrases that introduce hypothetical situations

No Comments

No Known Activations