INDEX

Explanations

phrases indicating lack of knowledge or information

oai_token-act-pair · gpt-3.5-turbo

expressions of uncertainty or a lack of knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

don

-0.71

eder

-0.67

eneg

-0.67

aud

-0.67

eworthy

-0.66

 ILCS

-0.66

ternity

-0.66

gar

-0.63

eding

-0.62

eded

-0.62

POSITIVE LOGITS

 idea

1.14

ually

1.13

 Idea

0.86

 concept

0.86

 moot

0.82

 Ideas

0.82

 ideas

0.77

 premise

0.76

Ì¶

0.74

 proposition

0.73

Activations Density 0.018%

phrases indicating lack of knowledge or information

expressions of uncertainty or a lack of knowledge

No Comments

No Known Activations