INDEX

Explanations

photo captions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "photos."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 variance

-0.68

 defender

-0.66

 mouth

-0.65

 exponent

-0.63

 problem

-0.62

 tract

-0.61

 arise

-0.61

emouth

-0.61

 base

-0.61

 branch

-0.61

POSITIVE LOGITS

Photos

4.10

 Photos

2.14

photos

2.05

Images

1.78

Phot

1.74

PHOTOS

1.69

Pict

1.67

Photo

1.56

photo

1.50

 photos

1.49

Activations Density 0.020%

photo captions

occurrences of the word "photos."

No Comments

No Known Activations