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

pite

-0.71

 Affect

-0.64

 Others

-0.63

rol

-0.62

 tick

-0.62

ross

-0.60

uka

-0.59

leon

-0.58

istrate

-0.58

puff

-0.58

POSITIVE LOGITS

 Galile

0.75

 confir

0.75

SPONSORED

0.73

Charges

0.71

Ì¶

0.71

 Droid

0.69

ãĤ¦ãĤ¹

0.67

erity

0.67

ãĥ¼ãĥ

0.66

 Princ

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.