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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yip

-0.76

aughed

-0.74

 msec

-0.73

ablishment

-0.67

ppelin

-0.67

ibaba

-0.65

ircraft

-0.65

 pens

-0.65

igate

-0.64

 Carly

-0.63

POSITIVE LOGITS

]}

0.69

ISA

0.69

HB

0.69

 Muller

0.67

 Dragonbound

0.67

interstitial

0.67

"],"

0.66

Skip

0.65

uli

0.65

ulo

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.