INDEX

Explanations

positive or negative affirmations

oai_token-act-pair · gpt-3.5-turbo

expressions emphasizing the concepts of "everything" and "nothing."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

egal

-0.69

clus

-0.67

 anonymity

-0.65

 lucrative

-0.64

iership

-0.64

akedown

-0.63

ocratic

-0.62

 touring

-0.60

Rih

-0.60

 priesthood

-0.60

POSITIVE LOGITS

Else

1.00

nces

0.96

body

0.91

 Else

0.91

 Dreams

0.91

 else

0.86

 Comes

0.79

 Begins

0.76

 Matters

0.73

 Changes

0.72

Activations Density 0.083%

positive or negative affirmations

expressions emphasizing the concepts of "everything" and "nothing."

No Comments

No Known Activations