INDEX

Explanations

mathematical equations and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

neſs

-1.04

NUMX

-1.02

ſelves

-0.97

ſelf

-0.95

 ―――――

-0.89

 pleaſure

-0.87

wiſe

-0.86

 purpoſe

-0.86

 itſelf

-0.84

 houſe

-0.82

POSITIVE LOGITS

0.69

 vean

0.66

«

0.66

0.65

»

0.63

0.60

0.59

«

0.59

0.58

0.57

Activations Density 2.736%

mathematical equations and expressions

No Comments

No Known Activations