INDEX

Explanations

specific actions or observations within a sentence, such as noticing, discovering, or finding

oai_token-act-pair · gpt-3.5-turbo

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

youtube

-0.68

ula

-0.66

ugal

-0.65

hattan

-0.62

charge

-0.62

duty

-0.61

href

-0.61

raviolet

-0.61

phrine

-0.61

osc

-0.60

POSITIVE LOGITS

 unmist

0.90

 similarities

0.88

how

0.83

 nothing

0.82

 what

0.81

 none

0.80

 plenty

0.79

 myriad

0.79

 something

0.79

 startling

0.78

Activations Density 0.267%

specific actions or observations within a sentence, such as noticing, discovering, or finding

No Comments

No Known Activations