INDEX

Explanations

strong, action-oriented language related to pushing boundaries, limits, and envelopes

oai_token-act-pair · gpt-3.5-turbo

phrases related to pushing boundaries or limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

efe

-0.67

SEA

-0.65

cin

-0.64

nces

-0.63

paying

-0.62

ottest

-0.61

cence

-0.61

cise

-0.60

/-

-0.60

 consulted

-0.60

POSITIVE LOGITS

 boundaries

1.48

 envelope

1.41

 buttons

1.22

 limits

1.21

 button

1.12

 onward

0.97

 Limits

0.96

 harder

0.95

 wedge

0.95

 boundary

0.90

Activations Density 0.214%

strong, action-oriented language related to pushing boundaries, limits, and envelopes

phrases related to pushing boundaries or limits

No Comments

No Known Activations