INDEX

Explanations

statements or actions indicating progress or change

oai_token-act-pair · gpt-3.5-turbo

phrases indicating actions taken or steps proposed in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Corpus

-0.75

 Sheep

-0.69

 Hitch

-0.68

 Chains

-0.67

 Waste

-0.66

Bie

-0.66

 Anch

-0.65

ench

-0.64

 peas

-0.63

 Lies

-0.63

POSITIVE LOGITS

 toward

0.81

 precautions

0.77

ndum

0.74

 remed

0.74

 steps

0.73

 backward

0.72

ãĤ¸

0.71

 towards

0.70

 proactive

0.68

 offline

0.68

Activations Density 0.064%

statements or actions indicating progress or change

phrases indicating actions taken or steps proposed in various contexts

No Comments

No Known Activations