INDEX

Explanations

adjectives describing positive or exciting attributes

oai_token-act-pair · gpt-3.5-turbo

descriptors that convey enthusiasm and intrigue about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

hers

-0.80

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.75

rogens

-0.75

terness

-0.74

arettes

-0.73

headers

-0.73

none

-0.72

 blamed

-0.71

reasonable

-0.71

UTERS

-0.70

POSITIVE LOGITS

new

0.92

 tale

0.91

 adventure

0.88

 combination

0.87

 partnership

0.85

 infographic

0.83

 alliance

0.83

 interactive

0.82

duo

0.81

 story

0.81

Activations Density 0.189%

adjectives describing positive or exciting attributes

descriptors that convey enthusiasm and intrigue about various subjects

No Comments

No Known Activations