INDEX

Explanations

references to cakes

oai_token-act-pair · gpt-3.5-turbo

references to cakes

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

nesota

-0.78

ostics

-0.77

ENTION

-0.76

audi

-0.74

iveness

-0.72

selves

-0.69

 Lomb

-0.69

 Cheong

-0.67

agonists

-0.65

 Fargo

-0.64

POSITIVE LOGITS

 cake

0.94

cakes

0.91

meal

0.90

cake

0.89

 cakes

0.88

 batter

0.87

walk

0.83

pillar

0.82

balls

0.79

fruit

0.78

Activations Density 0.018%

references to cakes

references to cakes

No Comments

No Known Activations