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

abad

-0.72

aur

-0.71

opers

-0.69

ception

-0.66

NSA

-0.66

Ã¶n

-0.65

liction

-0.65

flies

-0.63

eve

-0.63

aches

-0.63

POSITIVE LOGITS

 local

1.12

 Local

0.91

Local

0.88

 locally

0.88

local

0.85

xual

0.77

0.75

 locals

0.73

Percent

0.68

LOC

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.