INDEX

Explanations

phrases indicating worthiness or value

oai_token-act-pair · gpt-3.5-turbo

expressions of subjective opinions about experiences or situations

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

avage

-0.67

hips

-0.66

 Passenger

-0.64

pta

-0.63

lav

-0.63

currently

-0.60

erved

-0.60

stellar

-0.59

 pockets

-0.59

 VIEW

-0.59

POSITIVE LOGITS

alian

1.09

chy

1.06

self

0.87

ueller

0.83

 raining

0.83

 happens

0.82

iner

0.82

unes

0.81

icult

0.81

atic

0.79

Activations Density 0.132%

phrases indicating worthiness or value

expressions of subjective opinions about experiences or situations

No Comments

No Known Activations