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

leck

-0.80

onna

-0.77

ensional

-0.76

etheus

-0.73

enger

-0.73

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.69

itta

-0.68

ataka

-0.68

 Cumm

-0.67

itory

-0.66

POSITIVE LOGITS

pour

0.64

 Country

0.64

 Mexicans

0.64

emetery

0.63

orses

0.60

BLM

0.59

 obligated

0.59

chu

0.58

live

0.57

 Latvia

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.