INDEX

Explanations

new information or reports

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "new" in various contexts

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

cius

-0.99

 actionGroup

-0.78

Zip

-0.78

ashtra

-0.74

lua

-0.72

omever

-0.72

rice

-0.69

mop

-0.67

urations

-0.67

usercontent

-0.67

POSITIVE LOGITS

bie

1.12

 YORK

0.98

bies

0.96

 arrivals

0.94

 additions

0.91

 revelations

0.90

 developments

0.90

 batch

0.88

 generation

0.87

 revelation

0.86

Activations Density 0.093%

new information or reports

the presence of the word "new" in various contexts

No Comments

No Known Activations