INDEX

Explanations

years mentioned in sentences

oai_token-act-pair · gpt-3.5-turbo

specific years related to significant events or actions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

gib

-0.66

EStreamFrame

-0.65

bip

-0.60

ype

-0.59

 rusty

-0.58

 subst

-0.58

hed

-0.57

 ship

-0.57

icate

-0.57

venge

-0.57

POSITIVE LOGITS

-'

0.97

 onwards

0.85

å¹

0.84

bard

0.70

ixties

0.69

assetsadobe

0.68

 onward

0.67

ividual

0.67

0.66

BCE

0.64

Activations Density 0.150%

years mentioned in sentences

specific years related to significant events or actions

No Known Activations