INDEX

Explanations

keywords related to faithfulness or loyalty

oai_token-act-pair · gpt-3.5-turbo

references to faithfulness and fidelity

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

NetMessage

-0.71

Han

-0.71

asta

-0.71

 Marketable

-0.70

ISM

-0.68

 Cheong

-0.67

 Universities

-0.66

 Drugs

-0.66

Sing

-0.64

Klu

-0.64

POSITIVE LOGITS

 faithful

1.26

iciary

0.89

 worsh

0.87

sembly

0.85

 adherents

0.84

atile

0.84

 adherence

0.83

 faithfully

0.83

 adherent

0.83

 fidelity

0.83

Activations Density 0.008%

keywords related to faithfulness or loyalty

references to faithfulness and fidelity

No Comments

No Known Activations