INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ifully

-0.75

cially

-0.73

VERTISEMENT

-0.70

erred

-0.68

HAM

-0.63

walker

-0.63

rary

-0.62

mark

-0.62

orer

-0.62

itbart

-0.61

POSITIVE LOGITS

Xi

0.75

nery

0.70

nas

0.69

instein

0.67

 Jungle

0.63

 Sonia

0.63

SQU

0.61

ubis

0.60

uminati

0.60

 Bulg

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.