INDEX

Explanations

instances of things being left behind or affected negatively by events

oai_token-act-pair · gpt-3.5-turbo

phrases indicating abandonment or aftermath

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

externalActionCode

-0.66

intend

-0.65

buster

-0.64

 predec

-0.64

 prin

-0.63

STE

-0.61

wcsstore

-0.61

andise

-0.61

displayText

-0.60

percent

-0.60

POSITIVE LOGITS

overs

1.00

 undone

0.95

 untold

0.80

 unexpl

0.79

 unanswered

0.79

 unexplained

0.78

 scars

0.78

him

0.75

oir

0.74

 untreated

0.74

Activations Density 0.031%

instances of things being left behind or affected negatively by events

phrases indicating abandonment or aftermath

No Comments

No Known Activations