INDEX

Explanations

phrases indicating consideration or taking into account different factors

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

Torrent

-0.74

)]

-0.65

meg

-0.64

/?

-0.64

tumblr

-0.62

<?

-0.62

rier

-0.62

MpServer

-0.61

Jet

-0.60

"}

-0.60

POSITIVE LOGITS

 factors

1.04

 probabilities

0.97

WHY

0.95

 surroundings

0.95

 risks

0.94

 whether

0.93

 consequences

0.93

 facts

0.92

 considerations

0.91

 carefully

0.91

Activations Density 0.260%

phrases indicating consideration or taking into account different factors

No Comments

No Known Activations