INDEX

Explanations

phrases related to various technical or specific terms

oai_token-act-pair · gpt-3.5-turbo

specific nouns and terms related to various categories, including disease, environment, and cultural references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

enegger

-0.67

milo

-0.61

mble

-0.61

lished

-0.61

hyde

-0.58

ourke

-0.55

ulhu

-0.54

ä»£

-0.54

emale

-0.53

*/(

-0.51

POSITIVE LOGITS

ÂŃ

0.53

bugs

0.51

 agriculture

0.47

pal

0.46

âĢĲ

0.45

Sik

0.44

otin

0.44

 proportions

0.43

 warfare

0.43

 concentrations

0.43

Activations Density 0.962%

phrases related to various technical or specific terms

specific nouns and terms related to various categories, including disease, environment, and cultural references

No Comments

No Known Activations