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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AIN

-0.69

]=

-0.69

hawks

-0.67

 congr

-0.66

 Janeiro

-0.66

Hat

-0.65

rings

-0.65

ãĤ°

-0.65

ivals

-0.64

hire

-0.63

POSITIVE LOGITS

iosyncr

0.70

 independ

0.70

 todd

0.70

 loosen

0.67

 rese

0.66

 enrol

0.66

pend

0.65

pul

0.65

 kick

0.64

 watts

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.