INDEX

Explanations

different types or levels of something

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to various categories or classifications

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

arton

-0.66

ocalypse

-0.60

 deadliest

-0.60

waukee

-0.60

moon

-0.59

NOT

-0.58

efficiency

-0.57

Optional

-0.57

dq

-0.57

CTV

-0.57

POSITIVE LOGITS

 differing

0.93

 sexes

0.90

 different

0.90

 depending

0.89

 configurations

0.89

 styles

0.86

 architectures

0.80

 perspectives

0.80

 varying

0.78

 factions

0.78

Activations Density 0.284%

different types or levels of something

phrases that refer to various categories or classifications

No Comments

No Known Activations