INDEX

Explanations

phrases related to asserting claims or stating facts along with duration indicators

oai_token-act-pair · gpt-3.5-turbo

phrases indicating ongoing actions or situations

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

é¾į

-0.73

GROUP

-0.68

inki

-0.66

iru

-0.66

ãĥ¯ãĥ³

-0.64

IONS

-0.62

oval

-0.60

))))

-0.60

emi

-0.58

window

-0.58

POSITIVE LOGITS

 since

1.61

 lately

1.46

since

1.26

 previously

1.12

 hitherto

1.11

 previous

1.02

 awhile

0.98

 decades

0.96

 millennia

0.95

 repeatedly

0.95

Activations Density 1.615%

phrases related to asserting claims or stating facts along with duration indicators

phrases indicating ongoing actions or situations

No Comments

No Known Activations