INDEX

Explanations

phrases related to controversies or disputes

oai_token-act-pair · gpt-3.5-turbo

topics related to film, culture, and social commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Username

-0.71

 Certification

-0.69

 Specific

-0.64

 Effective

-0.62

Pwr

-0.61

 certification

-0.60

 Joint

-0.60

 Extension

-0.59

 Backup

-0.59

 Announce

-0.58

POSITIVE LOGITS

 drowned

0.70

 passers

0.69

 drown

0.67

 decad

0.65

 sprinkled

0.64

 throb

0.64

 tales

0.63

 culmin

0.62

 towering

0.62

 flung

0.61

Activations Density 2.476%

phrases related to controversies or disputes

topics related to film, culture, and social commentary

No Comments

No Known Activations