INDEX

Explanations

numeric values related to units or measurements

oai_token-act-pair · gpt-3.5-turbo

references to a specific unit or category 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

vous

-0.89

issance

-0.74

fter

-0.69

ãĤī

-0.68

byss

-0.67

aukee

-0.66

bone

-0.65

lli

-0.65

 Shack

-0.65

opard

-0.65

POSITIVE LOGITS

mate

0.95

mates

0.89

imet

0.82

rity

0.81

 units

0.81

ary

0.75

arily

0.74

 unit

0.73

imate

0.70

aries

0.69

Activations Density 0.026%

numeric values related to units or measurements

references to a specific unit or category in various contexts

No Comments

No Known Activations