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

WER

-0.75

\\\\\\\\

-0.75

âĺħ

-0.71

 Preferred

-0.69

DPR

-0.66

ONSORED

-0.60

olars

-0.60

 WHERE

-0.60

peak

-0.60

@@@@@@@@

-0.58

POSITIVE LOGITS

liest

0.80

vasive

0.71

uclear

0.71

Downloadha

0.69

leaf

0.68

vol

0.67

ometric

0.67

rawdownloadcloneembedreportprint

0.66

egu

0.65

patient

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.