INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

imus

-0.74

hetics

-0.71

oway

-0.70

 Baptist

-0.70

pheus

-0.69

ocus

-0.68

uther

-0.68

yrus

-0.67

aptic

-0.66

itars

-0.66

POSITIVE LOGITS

theless

0.79

netflix

0.77

env

0.62

 antidote

0.61

Hig

0.61

 battlefield

0.61

 harb

0.58

 acron

0.58

ned

0.58

 complied

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.