INDEX

Explanations

the word "model"

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 @ 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

azar

-0.90

ulhu

-0.86

vernment

-0.83

èª

-0.83

omes

-0.73

olulu

-0.71

omen

-0.71

kefeller

-0.70

reath

-0.68

pin

-0.67

POSITIVE LOGITS

model

0.80

 organism

0.79

 Mayhem

0.75

models

0.69

 Penal

0.69

)=(

0.69

 Operator

0.66

ered

0.65

urer

0.62

 Blueprint

0.62

Activations Density 0.036%

the word "model"

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

No Comments

No Known Activations