INDEX

Explanations

phrases indicating a consequence or outcome

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a result or consequence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

dayName

-0.61

displayText

-0.60

MpServer

-0.59

 Cosponsors

-0.59

 Packs

-0.58

 share

-0.58

visors

-0.58

ItemTracker

-0.58

intend

-0.57

 TOUR

-0.56

POSITIVE LOGITS

 undone

1.00

overs

0.98

oir

0.81

ipp

0.74

 unexplained

0.73

wich

0.73

lem

0.69

 untreated

0.69

hift

0.68

mia

0.68

Activations Density 0.039%

phrases indicating a consequence or outcome

phrases that indicate a result or consequence

No Comments

No Known Activations