INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

soDeliveryDate

-0.95

 projects

-0.67

 PATH

-0.66

UR

-0.64

 feasibility

-0.63

hops

-0.63

 Appears

-0.62

hesis

-0.62

URI

-0.61

::::::::

-0.60

POSITIVE LOGITS

 Schneider

0.68

circle

0.67

ertodd

0.65

 Sutherland

0.64

æ©Ł

0.64

shield

0.63

 Santos

0.62

 reckoning

0.62

roth

0.61

oles

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.