INDEX

Explanations

terms related to distribution and contribution

oai_token-act-pair · gpt-3.5-turbo

terms related to distribution and contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 è£ıè

-0.73

hor

-0.67

 knot

-0.65

 openings

-0.64

 disturb

-0.63

Hor

-0.63

Xan

-0.62

 uncomfortable

-0.62

 scratch

-0.62

 discomfort

-0.62

POSITIVE LOGITS

ribution

3.71

ributed

3.45

ribut

3.43

ributes

3.04

ribute

2.71

inguished

1.68

rib

1.25

aliation

1.25

rition

1.18

ractor

1.16

Activations Density 0.018%

terms related to distribution and contribution

terms related to distribution and contributions

No Comments

No Known Activations