INDEX

Explanations

structured programming constructs, like function definitions and conditional statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 &___

-0.52

ivar

-0.51

les

-0.49

transQ

-0.48

IContainer

-0.46

plish

-0.46

μο

-0.46

core

-0.46

ino

-0.46

 marito

-0.45

POSITIVE LOGITS

 pleaſure

0.76

 myſelf

0.73

 ſtate

0.71

AxisAlignment

0.69

 purpoſe

0.66

 sèche

0.65

 reaſon

0.65

contentLoaded

0.64

URLException

0.63

 Houſe

0.63

Activations Density 0.066%

structured programming constructs, like function definitions and conditional statements

No Comments

No Known Activations