INDEX

Explanations

phrases related to open-ended activities or concepts

oai_token-act-pair · gpt-3.5-turbo

phrases indicating open-endedness or flexibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ulhu

-0.78

 Khan

-0.77

Zam

-0.77

 Torres

-0.74

 Imran

-0.73

 Moreno

-0.70

Phi

-0.70

 Roberts

-0.69

 Schumer

-0.69

 Shah

-0.68

POSITIVE LOGITS

minded

1.17

bodied

1.11

space

1.11

eyed

1.10

poll

1.10

advertising

1.00

label

0.99

enough

0.99

circ

0.99

skinned

0.97

Activations Density 0.059%

phrases related to open-ended activities or concepts

phrases indicating open-endedness or flexibility

No Comments

No Known Activations