INDEX

Explanations

references to units or measurements

oai_token-act-pair · gpt-3.5-turbo

references to different types of units or measurements

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

vous

-0.84

fter

-0.69

bone

-0.68

é»Ĵ

-0.68

issance

-0.67

romeda

-0.66

æĢ

-0.66

byss

-0.66

=-=-

-0.66

ãĤī

-0.66

POSITIVE LOGITS

mate

0.91

rity

0.89

imet

0.88

mates

0.85

 units

0.85

 unit

0.75

arily

0.75

iates

0.74

itatively

0.73

matically

0.73

Activations Density 0.024%

references to units or measurements

references to different types of units or measurements

No Comments

No Known Activations