INDEX

Explanations

statements from various speakers

oai_token-act-pair · gpt-3.5-turbo

statements or quotes attributed to individuals

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

 silly

-0.74

 quiet

-0.73

 utter

-0.73

 silent

-0.73

 sleeper

-0.71

 patriot

-0.71

 unbeliev

-0.71

 sill

-0.70

 aven

-0.70

 merry

-0.69

POSITIVE LOGITS

 Instead

1.24

 Typically

1.20

 Moreover

1.19

 However

1.18

 Additionally

1.18

 Ideally

1.17

 Currently

1.17

 Conversely

1.16

 Similarly

1.16

 Previously

1.15

Activations Density 0.196%

statements from various speakers

statements or quotes attributed to individuals

No Comments

No Known Activations