INDEX

Explanations

phrases related to giving permission or enabling something to happen

oai_token-act-pair · gpt-3.5-turbo

phrases indicating permission or allowance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

soever

-0.81

edin

-0.74

itled

-0.67

UP

-0.65

 Originally

-0.65

weed

-0.64

jab

-0.64

 Rebell

-0.62

mond

-0.61

tags

-0.61

POSITIVE LOGITS

 greater

0.90

 extra

0.82

 mutual

0.80

 rapid

0.80

 speedy

0.79

 additional

0.77

 multiplication

0.76

 extensive

0.75

 redundancy

0.75

 further

0.75

Activations Density 0.075%

phrases related to giving permission or enabling something to happen

phrases indicating permission or allowance

No Comments

No Known Activations