INDEX

Explanations

references to alcoholic beverages, particularly wine

oai_token-act-pair · gpt-3.5-turbo

references to wine and alcoholic beverages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ulation

-0.79

aneously

-0.77

aneous

-0.76

ilitary

-0.70

Tur

-0.70

pta

-0.68

vernment

-0.67

ãĤ¨ãĥ«

-0.66

rencies

-0.66

ULAR

-0.65

POSITIVE LOGITS

 tasting

1.31

 cellar

1.11

 grapes

1.10

 vinegar

1.09

 tast

1.09

 wine

1.06

gard

0.96

yards

0.95

 wines

0.95

 drinkers

0.95

Activations Density 0.038%

references to alcoholic beverages, particularly wine

references to wine and alcoholic beverages

No Comments

No Known Activations