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

 pity

-0.87

 mercy

-0.75

utonium

-0.73

 parity

-0.71

uno

-0.71

hex

-0.70

ideo

-0.70

age

-0.69

urses

-0.67

psons

-0.66

POSITIVE LOGITS

Interstitial

0.84

SPONSORED

0.80

RELATED

0.79

FUN

0.76

VERTISEMENT

0.76

ADVERTISEMENT

0.75

PHOTOS

0.75

Questions

0.74

Tokens

0.74

Introduced

0.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.