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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

checking

-0.75

wa

-0.70

Wa

-0.69

 Moose

-0.69

holm

-0.68

butt

-0.68

Els

-0.67

chance

-0.67

fee

-0.67

Bad

-0.66

POSITIVE LOGITS

 guiActiveUn

0.77

osite

0.77

Pog

0.69

 theaters

0.68

iple

0.66

 philosophers

0.66

MSN

0.65

enery

0.65

 speakers

0.64

 transmit

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.