INDEX

Explanations

tokens or symbols indicating parameters or settings associated with system configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 itſelf

-0.71

 houſe

-0.67

 ſon

-0.67

neſs

-0.67

 pleaſure

-0.66

ſelf

-0.64

 faſt

-0.63

 myſelf

-0.62

 Perſ

-0.61

 ſtate

-0.61

POSITIVE LOGITS

 ostavi

0.73

0.68

：

0.65

CharStream

0.64

 autorytatywna

0.64

 SIMBAD

0.63

numerusform

0.63

\#:

0.60

：

0.60

✨:

0.59

Activations Density 0.344%

tokens or symbols indicating parameters or settings associated with system configurations

No Comments

No Known Activations