INDEX

Explanations

comparisons using the word "like"

oai_token-act-pair · gpt-3.5-turbo

phrases that express similarity or comparison

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

Ô

-0.82

uers

-0.79

icators

-0.73

Whe

-0.70

essing

-0.70

ÂłÂłÂłÂł

-0.69

gins

-0.66

erenn

-0.64

ß

-0.63

BILITY

-0.63

POSITIVE LOGITS

lihood

1.22

lier

0.98

liest

0.85

 ours

0.75

liness

0.73

 hers

0.72

 drafts

0.72

minded

0.69

 yours

0.68

 minded

0.67

Activations Density 0.060%

comparisons using the word "like"

phrases that express similarity or comparison

No Comments

No Known Activations