INDEX

Explanations

phrases related to knowledge or knowing

oai_token-act-pair · gpt-3.5-turbo

instances of the word "know" and its variations

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

interstitial

-0.98

ItemTracker

-0.78

psey

-0.76

phrine

-0.74

avored

-0.73

conservancy

-0.73

*/(

-0.71

cffffcc

-0.70

adish

-0.69

atism

-0.69

POSITIVE LOGITS

ledge

1.15

lege

1.11

ledged

1.08

LED

0.91

ness

0.82

lean

0.78

ingly

0.78

lessly

0.76

ably

0.75

how

0.74

Activations Density 0.048%

phrases related to knowledge or knowing

instances of the word "know" and its variations

No Comments

No Known Activations