INDEX

Explanations

alphanumeric strings mixed with colloquial text, which seem to be related to technology or industry-specific jargon

oai_token-act-pair · gpt-3.5-turbo

references to wind energy technology and its applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Kro

-0.81

lesh

-0.81

meat

-0.80

Kab

-0.80

 kidney

-0.80

ylum

-0.80

Meat

-0.79

 Burger

-0.79

interstitial

-0.78

urger

-0.78

POSITIVE LOGITS

Wind

2.09

 Wind

2.06

 wind

2.06

 Winds

1.77

wind

1.74

 winds

1.64

 Weather

1.63

 storms

1.59

Weather

1.55

 turbines

1.52

Activations Density 0.290%

alphanumeric strings mixed with colloquial text, which seem to be related to technology or industry-specific jargon

references to wind energy technology and its applications

No Comments

No Known Activations