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

 subp

-0.72

nz

-0.71

zee

-0.68

Footnote

-0.65

nis

-0.63

ãĤ§

-0.63

Zone

-0.63

earch

-0.62

lif

-0.62

ESV

-0.62

POSITIVE LOGITS

nuts

0.74

pod

0.70

":[

0.66

 consequential

0.62

 Weinstein

0.61

nut

0.61

oteric

0.59

erk

0.59

Pod

0.58

Yao

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.