INDEX

Explanations

words related to making decisions or comparisons based on specific criteria

oai_token-act-pair · gpt-3.5-turbo

phrases centered around the concept of being dependent on criteria or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ivas

-0.66

rette

-0.64

chip

-0.64

aed

-0.63

nel

-0.62

jar

-0.61

lain

-0.61

IRT

-0.60

 Kinnikuman

-0.60

Preview

-0.60

POSITIVE LOGITS

 guiActiveUn

0.72

itiz

0.66

 circumstances

0.64

 favour

0.63

 injection

0.62

 sidew

0.62

 mater

0.61

 administrations

0.60

 favoring

0.60

cf

0.59

Activations Density 0.159%

words related to making decisions or comparisons based on specific criteria

phrases centered around the concept of being dependent on criteria or conditions

No Comments

No Known Activations