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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erton

-0.69

eele

-0.69

nown

-0.68

scill

-0.66

hett

-0.66

ometown

-0.65

itals

-0.64

urable

-0.64

elt

-0.64

igslist

-0.64

POSITIVE LOGITS

cream

0.67

bug

0.66

iov

0.65

 Vulkan

0.64

eating

0.64

 Norn

0.63

fish

0.63

bee

0.62

blown

0.61

kamp

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.