INDEX

Explanations

the word "honest" and phrases related to honesty

oai_token-act-pair · gpt-3.5-turbo

instances of the word "honest" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

lav

-0.74

anus

-0.72

anian

-0.71

 Supplement

-0.71

oval

-0.71

acid

-0.70

interrupted

-0.70

fleet

-0.69

joined

-0.68

 Krish

-0.68

POSITIVE LOGITS

 broker

0.92

 honest

0.83

 appraisal

0.81

 truthful

0.76

 honesty

0.73

 dealings

0.73

 mistake

0.71

 mistakes

0.69

 candid

0.69

spection

0.67

Activations Density 0.039%

the word "honest" and phrases related to honesty

instances of the word "honest" and its variations

No Comments

No Known Activations