INDEX

Explanations

phrases expressing strong opinions or emotions towards certain actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "that" in various contexts

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

aciously

-0.71

vre

-0.70

roy

-0.67

ugu

-0.65

roach

-0.65

Bow

-0.63

nec

-0.63

Desk

-0.62

dry

-0.61

 WATCHED

-0.61

POSITIVE LOGITS

 accompanies

1.34

 awaits

1.20

 occurs

1.12

 entails

1.11

 surrounds

1.09

 separates

1.03

 exists

1.00

 arises

0.99

 ensued

0.97

 occurred

0.97

Activations Density 0.155%

phrases expressing strong opinions or emotions towards certain actions or behaviors

instances of the phrase "that" in various contexts

No Comments

No Known Activations