INDEX

Explanations

medical terms or words related to healthcare

oai_token-act-pair · gpt-3.5-turbo

topics related to health and medical research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 UNCLASSIFIED

-0.86

anwhile

-0.85

etheless

-0.73

pse

-0.65

âķĲ

-0.64

 Azerb

-0.61

)."

-0.61

.).

-0.61

theless

-0.60

[*

-0.60

POSITIVE LOGITS

 âĢº

0.76

 Belfast

0.71

 âĢİ

0.68

âĢİ

0.59

 lately

0.57

Skip

0.56

 Posted

0.55

 cryptocurrency

0.54

Â¶

0.54

 LEGO

0.53

Activations Density 1.561%

medical terms or words related to healthcare

topics related to health and medical research

No Comments

No Known Activations