INDEX

Explanations

descriptions related to significant events or changes

oai_token-act-pair · gpt-3.5-turbo

conversations about significant events or achievements

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

 Fires

-0.73

 Telesc

-0.73

 Spit

-0.73

 Machines

-0.71

 Sins

-0.69

 Chatt

-0.69

ãĥĺ

-0.69

 Nose

-0.69

 Beet

-0.68

é¾įå

-0.66

POSITIVE LOGITS

animous

0.69

 effort

0.67

 clutch

0.66

 informative

0.65

 ambitious

0.64

 approach

0.63

 annotation

0.62

 momentum

0.61

 advisory

0.60

 emph

0.60

Activations Density 0.126%

descriptions related to significant events or changes

conversations about significant events or achievements

No Comments

No Known Activations