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

zn

-0.71

 persecuted

-0.65

cry

-0.64

 bubble

-0.62

prus

-0.61

unal

-0.61

ossom

-0.60

 prompt

-0.60

 constit

-0.60

igate

-0.59

POSITIVE LOGITS

 Availability

0.82

 Showdown

0.81

MSN

0.79

 GOODMAN

0.76

ural

0.76

AAF

0.76

 Quantity

0.73

 Aerial

0.71

 Tycoon

0.70

 Alert

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.