INDEX

Explanations

action verbs in the present tense

oai_token-act-pair · gpt-3.5-turbo

phrases that begin with the word "start."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

illard

-0.73

asca

-0.72

itsch

-0.71

iliary

-0.71

ault

-0.71

ugs

-0.70

bey

-0.70

obi

-0.66

ortium

-0.66

rone

-0.65

POSITIVE LOGITS

starting

1.00

nings

0.94

 anew

0.81

rek

0.72

strap

0.72

ctors

0.70

started

0.70

ctor

0.70

OPLE

0.69

ITIES

0.69

Activations Density 0.046%

action verbs in the present tense

phrases that begin with the word "start."

No Comments

No Known Activations