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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tail

-0.75

eret

-0.74

 bean

-0.72

inge

-0.69

ãĤ´ãĥ³

-0.68

unks

-0.68

 hemisphere

-0.67

ught

-0.67

pload

-0.66

ives

-0.66

POSITIVE LOGITS

tics

0.72

tical

0.71

yth

0.69

 viol

0.66

MSN

0.65

 Ibid

0.63

viol

0.61

alien

0.61

hetically

0.61

 Crim

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.