INDEX

Explanations

phrases related to specific locations or events

oai_token-act-pair · gpt-3.5-turbo

key phrases related to locations and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Blossom

-0.90

Ba

-0.84

 Bowen

-0.84

ubi

-0.82

Wr

-0.80

 Clemson

-0.79

berry

-0.79

 Biden

-0.78

bush

-0.78

 Choi

-0.78

POSITIVE LOGITS

Met

2.36

Met

2.23

MET

2.07

met

2.01

met

1.88

MET

1.79

 metab

1.42

 Metall

1.38

 Meter

1.28

emet

1.24

Activations Density 0.200%

phrases related to specific locations or events

key phrases related to locations and events

No Comments

No Known Activations