INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Magazine

-0.71

VK

-0.67

Pin

-0.66

 contraceptives

-0.65

Haw

-0.63

CHAPTER

-0.62

iculty

-0.62

ordering

-0.61

Sexual

-0.61

]"

-0.61

POSITIVE LOGITS

rees

0.72

HL

0.67

ipers

0.66

Lei

0.66

RB

0.65

WS

0.62

oros

0.61

 Remem

0.60

LE

0.59

ifa

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.