INDEX

Explanations

past tense verbs indicating the starting of an action or event

oai_token-act-pair · gpt-3.5-turbo

instances of the word "started" or "began," indicating the initiation of actions

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

 entirety

-0.76

alted

-0.73

ighth

-0.72

ugs

-0.71

âĨĳ

-0.69

obi

-0.67

omb

-0.66

cit

-0.65

icol

-0.65

etry

-0.65

POSITIVE LOGITS

 anew

0.98

 hemor

0.79

 dating

0.76

 PRESS

0.76

 fuss

0.75

ŃĶ

0.74

 raining

0.73

 noticing

0.71

nings

0.70

 behaving

0.69

Activations Density 0.070%

past tense verbs indicating the starting of an action or event

instances of the word "started" or "began," indicating the initiation of actions

No Comments

No Known Activations