INDEX

Explanations

phrases related to hats or headwear

oai_token-act-pair · gpt-3.5-turbo

references to hats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 UNIVERS

-0.69

 Supplementary

-0.67

ateral

-0.65

 TEST

-0.64

 Decay

-0.63

theless

-0.63

MSM

-0.62

 glutamate

-0.62

 Rhod

-0.60

CLS

-0.60

POSITIVE LOGITS

chet

1.39

chery

1.31

hat

1.16

 hats

1.09

cher

1.00

 brim

0.91

ches

0.91

glers

0.90

emaker

0.87

eless

0.86

Activations Density 0.007%

phrases related to hats or headwear

references to hats

No Comments

No Known Activations