INDEX

Explanations

news headlines with phrases indicating additional information or updates

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "more" or related phrases emphasizing an increase or continuation

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

xtap

-0.91

ader

-0.81

uckle

-0.72

keeping

-0.72

wered

-0.69

ãĥ¼ãĥĨ

-0.68

mobi

-0.68

itude

-0.67

itudes

-0.67

ĺħ

-0.67

POSITIVE LOGITS

 than

1.09

HUD

0.79

ado

0.79

 interesting

0.78

 info

0.75

 attractive

0.74

 importantly

0.73

 detailed

0.72

 exciting

0.72

 VIDEOS

0.71

Activations Density 0.042%

news headlines with phrases indicating additional information or updates

occurrences of the word "more" or related phrases emphasizing an increase or continuation

No Comments

No Known Activations