INDEX

Explanations

phrases related to a particular way of living or doing things

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate methods or ways of doing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

naires

-0.73

 Bots

-0.70

sites

-0.69

 Extras

-0.65

isite

-0.64

Klu

-0.63

UAL

-0.62

 Conditions

-0.62

Guest

-0.61

 Shades

-0.61

POSITIVE LOGITS

 communicating

0.96

 dealing

0.94

 coping

0.92

 interpreting

0.92

 reckoning

0.90

 ascert

0.83

 navigating

0.81

 life

0.81

 thinking

0.80

phr

0.80

Activations Density 0.043%

phrases related to a particular way of living or doing things

phrases that indicate methods or ways of doing something

No Comments

No Known Activations