INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

efer

-0.72

CSI

-0.71

ngth

-0.66

 Godd

-0.66

ossibility

-0.65

rast

-0.65

vernment

-0.64

estate

-0.64

joice

-0.64

flix

-0.63

POSITIVE LOGITS

 moderates

0.67

 wounding

0.65

Anth

0.64

mes

0.63

jah

0.63

knit

0.62

Nusra

0.62

mere

0.61

 extremes

0.60

ensable

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.