INDEX

Explanations

references to articles or op-eds

oai_token-act-pair · gpt-3.5-turbo

occurrences of the preposition "in" within various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 incumb

-0.72

 snipers

-0.70

 unnecess

-0.68

 ingred

-0.67

 combatants

-0.65

»Ĵ

-0.64

ĺħ

-0.64

soever

-0.61

ļ

-0.60

âĿ

-0.60

POSITIVE LOGITS

 lieu

1.24

 conjunction

1.09

 regards

1.07

 favor

0.98

 accordance

0.96

 relation

0.96

clus

0.96

 vitro

0.93

 chronological

0.93

organic

0.90

Activations Density 0.303%

references to articles or op-eds

occurrences of the preposition "in" within various contexts

No Comments

No Known Activations