INDEX

Explanations

phrases indicating events or actions occurring or continuing up until a specific point

oai_token-act-pair · gpt-3.5-turbo

phrases indicating ongoing situations or conditions until a specified endpoint is reached

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

 Actions

-0.70

groupon

-0.69

 Holding

-0.67

RSS

-0.67

oft

-0.66

 Bind

-0.62

gravity

-0.62

 Categories

-0.62

 ----------------

-0.62

 Sense

-0.61

POSITIVE LOGITS

 expires

0.75

 reaches

0.73

 perfected

0.72

 ende

0.69

isode

0.69

 settle

0.69

emetery

0.68

 rematch

0.67

 finally

0.66

pup

0.66

Activations Density 0.121%

phrases indicating events or actions occurring or continuing up until a specific point

phrases indicating ongoing situations or conditions until a specified endpoint is reached

No Comments

No Known Activations