INDEX

Explanations

the name "Phillips" at different levels of relevance

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Phillips" or related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ERAL

-0.85

joined

-0.78

izen

-0.74

juven

-0.73

clud

-0.70

 Bihar

-0.69

quo

-0.69

venge

-0.68

flow

-0.68

rous

-0.67

POSITIVE LOGITS

 Phillips

0.97

 Parsons

0.85

 cones

0.78

ippi

0.76

sey

0.76

worth

0.76

 pedals

0.76

pie

0.75

nuts

0.74

 nails

0.73

Activations Density 0.009%

the name "Phillips" at different levels of relevance

mentions of the name "Phillips" or related variations

No Comments

No Known Activations