INDEX

Explanations

conditional statements and hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Majefty

-0.73

CppCodeGen

-0.70

 endforeach

-0.66

UnusedPrivate

-0.65

ensioni

-0.65

UrlResolution

-0.64

ArrowToggle

-0.64

 myſelf

-0.64

 dares

-0.63

stander

-0.63

POSITIVE LOGITS

 sounded

0.58

 sounds

0.56

 pretty

0.55

 suffice

0.55

 sound

0.54

 solve

0.53

 mean

0.53

 оригіналу

0.52

pretty

0.51

TagMode

0.50

Activations Density 0.360%

conditional statements and hypothetical scenarios

No Comments

No Known Activations