INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

hran

-0.82

hower

-0.75

hold

-0.72

.","

-0.72

ALE

-0.67

izabeth

-0.64

isSpecialOrderable

-0.64

 Mehran

-0.62

swick

-0.62

verse

-0.60

POSITIVE LOGITS

 sucks

0.65

cycl

0.63

 Dumb

0.62

Twe

0.61

killed

0.61

eng

0.60

ext

0.60

 dstg

0.60

 Frog

0.59

endered

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.