INDEX

Explanations

phrases related to opinions or beliefs

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "anyone who" followed by varying actions or characteristics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tails

-0.72

 Delicious

-0.68

urers

-0.67

ãĥĵ

-0.65

 Recovery

-0.62

abi

-0.60

 segregated

-0.59

 Beasts

-0.59

anity

-0.58

 Bake

-0.58

POSITIVE LOGITS

 knows

0.92

soever

0.85

perty

0.80

 wants

0.78

pires

0.77

 cares

0.76

 reads

0.74

 remembers

0.73

lvl

0.72

atever

0.69

Activations Density 0.076%

phrases related to opinions or beliefs

instances of the phrase "anyone who" followed by varying actions or characteristics

No Comments

No Known Activations