INDEX

Explanations

actions related to pilots and scanning or tapping interactions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 تانيه

-0.70

socket

-0.59

Decrement

-0.57

 Komisi

-0.55

abet

-0.54

reonine

-0.54

parseLong

-0.53

 Gottlieb

-0.53

 entertained

-0.52

Assemb

-0.52

POSITIVE LOGITS

tap

1.26

Tap

1.25

Tap

1.14

 scan

1.10

 taps

1.08

scan

1.05

tap

1.05

 SCAN

1.05

 scanning

1.02

scanning

1.01

Activations Density 0.032%

actions related to pilots and scanning or tapping interactions

No Comments

No Known Activations