INDEX

Explanations

phrases mentioning events or situations that attract significant public attention

oai_token-act-pair · gpt-3.5-turbo

mentions of newsworthy events or headlines

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

Not in Any Lists

No Comments

Negative Logits

ework

-0.76

 recip

-0.68

sis

-0.67

tein

-0.65

parent

-0.63

inite

-0.62

sim

-0.60

construct

-0.59

claimer

-0.59

optim

-0.58

POSITIVE LOGITS

 headlines

0.91

elight

0.82

rovers

0.82

 internationally

0.79

 notoriety

0.79

waves

0.78

icter

0.78

 Cosponsors

0.72

 domestically

0.68

 Hebdo

0.68

Activations Density 0.110%

phrases mentioning events or situations that attract significant public attention

mentions of newsworthy events or headlines

No Comments

No Known Activations