INDEX

Explanations

terms related to intensive care or tasks requiring intense effort

oai_token-act-pair · gpt-3.5-turbo

references to intensive activities or care 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

 Passage

-0.74

ulet

-0.66

 Hole

-0.66

allows

-0.66

omsky

-0.64

warm

-0.64

 Quinn

-0.61

DonaldTrump

-0.60

isphere

-0.60

opp

-0.60

POSITIVE LOGITS

ly

1.09

 intensive

1.00

mble

1.00

intensive

0.95

 outpatient

0.79

urally

0.78

icult

0.75

bred

0.74

LY

0.73

entimes

0.73

Activations Density 0.031%

terms related to intensive care or tasks requiring intense effort

references to intensive activities or care in various contexts

No Comments

No Known Activations