INDEX

Explanations

phrases related to official documents or announcements

oai_token-act-pair · gpt-3.5-turbo

words related to a specific type of promotional imagery or language in media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Seym

-0.67

resso

-0.65

 Rossi

-0.65

rete

-0.63

estation

-0.63

est

-0.62

 Archangel

-0.61

 Argon

-0.61

req

-0.60

 unfocusedRange

-0.60

POSITIVE LOGITS

ously

0.83

baum

0.78

ous

0.77

backer

0.76

olls

0.75

aceae

0.75

oster

0.75

osity

0.73

FORE

0.71

TAIN

0.71

Activations Density 0.061%

phrases related to official documents or announcements

words related to a specific type of promotional imagery or language in media

No Comments

No Known Activations