INDEX

Explanations

keywords related to infestations and data testing or validation

oai_token-act-pair · gpt-3.5-turbo

words related to infestation or being infested

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

pton

-0.71

tor

-0.71

brow

-0.67

 Kinnikuman

-0.67

vor

-0.66

gap

-0.64

lua

-0.62

 morbid

-0.60

blance

-0.59

tri

-0.59

POSITIVE LOGITS

ested

1.29

esting

1.03

icious

0.75

naire

0.72

icated

0.71

imated

0.70

imates

0.69

iary

0.68

OSED

0.67

ragon

0.67

Activations Density 0.007%

keywords related to infestations and data testing or validation

words related to infestation or being infested

No Comments

No Known Activations