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

 wills

-0.79

 wipes

-0.74

 councils

-0.72

 wors

-0.70

 hurricanes

-0.67

 soil

-0.67

 disappoint

-0.66

 millenn

-0.66

 schedules

-0.66

 believers

-0.65

POSITIVE LOGITS

fram

0.91

 Blumenthal

0.85

 âĶľ

0.79

Ã£o

0.78

OPA

0.78

xtap

0.76

phe

0.75

ici

0.75

alys

0.75

chat

0.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.