INDEX

Explanations

reserved words in a coding context

oai_token-act-pair · gpt-3.5-turbo

terms related to classification and specifications in a structured context

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

hots

-0.79

Commercial

-0.75

Indust

-0.74

hun

-0.72

greg

-0.72

recent

-0.71

ooters

-0.70

 acron

-0.70

ä¿

-0.69

certain

-0.69

POSITIVE LOGITS

 portion

1.41

 counterpart

1.21

 version

1.19

 side

1.16

 axis

1.10

 phase

1.08

 allele

1.05

 element

1.03

 aspect

1.02

 ones

1.01

Activations Density 0.275%

reserved words in a coding context

terms related to classification and specifications in a structured context

No Comments

No Known Activations