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

zees

-0.79

nah

-0.69

nsics

-0.69

utherford

-0.68

staking

-0.67

 pursu

-0.67

gow

-0.66

ript

-0.66

rots

-0.65

ritten

-0.65

POSITIVE LOGITS

é¾

0.68

aste

0.64

 Plot

0.64

OVA

0.63

 Grade

0.62

 Archdemon

0.61

Plot

0.61

 Premium

0.60

Gh

0.59

ADVERTISEMENT

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.