INDEX

Explanations

phrases indicating a consequence or outcome

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate consequences or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

alist

-0.67

displayText

-0.67

 predec

-0.63

dayName

-0.62

intend

-0.62

externalActionCode

-0.60

é¾

-0.60

ItemTracker

-0.59

STE

-0.59

MpServer

-0.59

POSITIVE LOGITS

overs

0.95

 undone

0.89

oir

0.76

lem

0.75

wich

0.73

hift

0.72

ings

0.72

 unexpl

0.72

ipp

0.71

 unexplained

0.69

Activations Density 0.033%

phrases indicating a consequence or outcome

phrases that indicate consequences or outcomes

No Comments

No Known Activations