INDEX

Explanations

temporal events or moments in time

oai_token-act-pair · gpt-3.5-turbo

the phrase "just before" followed by various times referenced in a narrative or chronological context

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

vari

-0.82

uph

-0.76

alian

-0.74

atis

-0.70

uity

-0.67

alam

-0.67

Helper

-0.65

amen

-0.65

orers

-0.63

bats

-0.62

POSITIVE LOGITS

çĶ°

0.72

 Azerb

0.67

 coast

0.66

onday

0.65

 sunrise

0.65

 Christmas

0.63

 Interstate

0.63

 Mellon

0.62

undown

0.60

 clipping

0.60

Activations Density 0.060%

temporal events or moments in time

the phrase "just before" followed by various times referenced in a narrative or chronological context

No Comments

No Known Activations