INDEX

Explanations

phrases related to asking about characteristics or qualities of something

oai_token-act-pair · gpt-3.5-turbo

phrases that inquire about types or examples of things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chy

-0.84

MY

-0.80

VEL

-0.77

NYSE

-0.69

enez

-0.68

PT

-0.68

äºĶ

-0.66

obyl

-0.66

steamapps

-0.65

pse

-0.64

POSITIVE LOGITS

etting

0.81

soever

0.70

atto

0.66

 accomplished

0.65

ucks

0.64

isms

0.64

onom

0.64

ata

0.63

really

0.62

 aber

0.62

Activations Density 0.022%

phrases related to asking about characteristics or qualities of something

phrases that inquire about types or examples of things

No Comments

No Known Activations