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

ittal

-0.67

casts

-0.64

issance

-0.64

 successive

-0.64

mberg

-0.64

immune

-0.63

gotten

-0.63

ibur

-0.61

ansion

-0.60

 Alban

-0.60

POSITIVE LOGITS

::::::::

0.68

 tomat

0.66

Pul

0.65

pse

0.64

å¥³

0.63

:/

0.63

 lime

0.63

 Sunshine

0.63

ouri

0.62

ãĥ¯ãĥ³

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.