INDEX

Explanations

phrases indicating willingness or action towards a particular outcome

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate actions or intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Flo

-0.73

 Uses

-0.71

 Ended

-0.67

 Fires

-0.66

 Concepts

-0.66

 Used

-0.65

 Eucl

-0.65

Klu

-0.64

 Lines

-0.64

 Drops

-0.62

POSITIVE LOGITS

 emulate

1.19

 promote

1.11

 improve

1.06

pless

1.05

 alleviate

1.02

 mitigate

1.02

 ensure

0.99

 conserve

0.98

 commemorate

0.96

 minimize

0.96

Activations Density 0.068%

phrases indicating willingness or action towards a particular outcome

phrases that indicate actions or intentions

No Comments

No Known Activations