INDEX

Explanations

phrases beginning with 'What'

oai_token-act-pair · gpt-3.5-turbo

interrogative phrases or questions that begin with "what"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulic

-0.65

lich

-0.63

trop

-0.62

 steril

-0.60

 indoors

-0.60

 congrat

-0.60

POR

-0.59

raction

-0.59

ages

-0.57

eer

-0.56

POSITIVE LOGITS

soever

1.38

 happens

1.08

 happened

1.05

 happ

0.99

 transpired

0.86

 kinds

0.86

nces

0.81

 sorts

0.79

 Lies

0.76

Cause

0.76

Activations Density 0.119%

phrases beginning with 'What'

interrogative phrases or questions that begin with "what"

No Comments

No Known Activations