INDEX

Explanations

phrases reflecting conversations or dialogues with varying emotional tones

oai_token-act-pair · gpt-3.5-turbo

emotional or exclamatory expressions often related to reactions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

NetMessage

-0.78

 tremend

-0.73

 weaving

-0.67

 scattering

-0.64

 psychiat

-0.64

bda

-0.63

 experien

-0.63

 lodging

-0.63

 recogn

-0.62

kj

-0.62

POSITIVE LOGITS

º

0.76

¦

0.73

Â¯

0.72

ĭ

0.72

aren

0.71

£

0.70

 Rapids

0.69

ickle

0.68

let

0.68

said

0.67

Activations Density 0.268%

phrases reflecting conversations or dialogues with varying emotional tones

emotional or exclamatory expressions often related to reactions or statements

No Comments

No Known Activations