INDEX

Explanations

phrases related to safety and accidents in operational environments

oai_token-act-pair · gpt-3.5-turbo

situations or contexts related to unexpected events or hazards

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

pires

-0.71

Untitled

-0.70

someone

-0.65

 itself

-0.64

 deserves

-0.64

Compat

-0.62

something

-0.62

Merit

-0.61

HAS

-0.61

 Himself

-0.60

POSITIVE LOGITS

 abound

1.03

 plentiful

0.74

 varying

0.73

 meanwhile

0.66

 apiece

0.65

 vary

0.64

 clustered

0.63

 likewise

0.63

 similarly

0.62

 prolifer

0.62

Activations Density 0.968%

phrases related to safety and accidents in operational environments

situations or contexts related to unexpected events or hazards

No Comments

No Known Activations