INDEX

Explanations

phrases indicating importance or emphasis

oai_token-act-pair · gpt-3.5-turbo

references to personal feelings and subjective experiences

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

culosis

-0.74

venge

-0.67

Exit

-0.67

classic

-0.63

arching

-0.62

oby

-0.61

fps

-0.61

ptives

-0.60

rocket

-0.60

Fu

-0.58

POSITIVE LOGITS

 strains

0.64

 anecd

0.61

beh

0.61

 acknowled

0.59

 agreement

0.59

IRD

0.58

 conceded

0.58

 arrangement

0.57

 overest

0.57

ather

0.57

Activations Density 0.539%

phrases indicating importance or emphasis

references to personal feelings and subjective experiences

No Comments

No Known Activations