INDEX

Explanations

references to exclusive access or privileges

oai_token-act-pair · gpt-3.5-turbo

mentions of exclusivity or exclusive content

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

apers

-0.86

;;;;;;;;;;;;

-0.81

aper

-0.79

olesterol

-0.78

annis

-0.75

psc

-0.74

abases

-0.73

ERO

-0.73

ttp

-0.73

 Refugees

-0.73

POSITIVE LOGITS

 exclus

0.84

 privileges

0.83

 exclusive

0.79

 exclusively

0.78

ities

0.77

 rights

0.76

 club

0.72

 insight

0.69

exclusive

0.67

 warr

0.67

Activations Density 0.011%

references to exclusive access or privileges

mentions of exclusivity or exclusive content

No Comments

No Known Activations