INDEX

Explanations

the word "model" or variations of it

oai_token-act-pair · gpt-3.5-turbo

references to a specific model, referred to as "Model 9"

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

azar

-0.87

ulhu

-0.84

èª

-0.80

omen

-0.77

OME

-0.71

kefeller

-0.71

olulu

-0.70

endo

-0.70

omes

-0.70

vernment

-0.69

POSITIVE LOGITS

 organism

0.81

 Mayhem

0.75

 Penal

0.73

model

0.73

)=(

0.68

 Operator

0.68

ered

0.67

models

0.66

 Reloaded

0.65

er

0.63

Activations Density 0.049%

the word "model" or variations of it

references to a specific model, referred to as "Model 9"

No Comments

No Known Activations