INDEX

Explanations

phrases containing the word "human"

oai_token-act-pair · gpt-3.5-turbo

references to humans and their characteristics or behaviors

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

arella

-0.78

angles

-0.75

RAG

-0.74

kick

-0.74

forth

-0.71

rypt

-0.70

wark

-0.70

ippi

-0.69

ãģĨ

-0.69

etsy

-0.68

POSITIVE LOGITS

 beings

1.18

 readable

0.99

 embryonic

0.99

oids

0.97

itarian

0.85

 rights

0.84

itar

0.81

 genome

0.81

 civilization

0.80

fra

0.78

Activations Density 0.023%

phrases containing the word "human"

references to humans and their characteristics or behaviors

No Comments

No Known Activations