INDEX

Explanations

proper nouns or specialized terms from various fields

oai_token-act-pair · gpt-3.5-turbo

references to specific subjects or entities, particularly in the context of their roles or impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

cffff

-0.84

netflix

-0.71

arov

-0.65

abytes

-0.63

enegger

-0.63

ĪĴ

-0.62

Downloadha

-0.62

olester

-0.62

itton

-0.61

conservancy

-0.61

POSITIVE LOGITS

 arrangement

0.75

 differs

0.69

 varies

0.68

 endeavor

0.68

 endeavors

0.66

 differ

0.65

 methodology

0.64

viz

0.64

toggle

0.63

 puzzle

0.62

Activations Density 0.528%

proper nouns or specialized terms from various fields

references to specific subjects or entities, particularly in the context of their roles or impacts

No Comments

No Known Activations