INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Oath

-0.93

 Rated

-0.74

Guard

-0.73

bow

-0.70

Ring

-0.65

 Proud

-0.63

 Viper

-0.63

TON

-0.60

ãĥ¬

-0.60

 Pledge

-0.60

POSITIVE LOGITS

ileaks

0.83

umped

0.77

adobe

0.76

icient

0.75

ensen

0.70

erent

0.70

aido

0.68

aucas

0.67

theless

0.67

iment

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.