INDEX

Explanations

company or organization names preceded by key information or updates

oai_token-act-pair · gpt-3.5-turbo

the word "the" in various contexts throughout the text

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

ago

-0.79

fw

-0.78

hops

-0.78

ients

-0.76

hei

-0.72

atures

-0.72

encies

-0.70

aho

-0.68

ature

-0.66

Games

-0.65

POSITIVE LOGITS

 slightest

1.15

 possibility

1.10

 presence

1.06

 inability

1.05

 extent

1.03

 emergence

1.03

 absence

1.02

 sheer

0.99

 notion

0.98

 aforementioned

0.97

Activations Density 0.149%

company or organization names preceded by key information or updates

the word "the" in various contexts throughout the text

No Comments

No Known Activations