INDEX

Explanations

phrases related to indications or signs of different situations or conditions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significant or notable events and their consequences

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

ãĥ¯

-0.78

 rounds

-0.68

FIG

-0.65

bc

-0.65

 Marketable

-0.64

Joined

-0.63

etsk

-0.62

Kee

-0.62

bridge

-0.60

CTV

-0.59

POSITIVE LOGITS

 impending

1.05

oneliness

0.80

 comr

0.76

 uniqueness

0.74

 magnitude

0.73

 specificity

0.72

 importance

0.70

escription

0.70

 conflic

0.69

 imminent

0.68

Activations Density 0.477%

phrases related to indications or signs of different situations or conditions

phrases indicating significant or notable events and their consequences

No Comments

No Known Activations