INDEX

Explanations

prepositions followed by abstract concepts or actions

oai_token-act-pair · gpt-3.5-turbo

prepositions and words indicating relationships or specifics about a topic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

quartered

-0.81

olitical

-0.81

quet

-0.79

ynthesis

-0.76

ires

-0.73

acy

-0.69

ashington

-0.68

ired

-0.67

ensable

-0.67

eteenth

-0.67

POSITIVE LOGITS

 somet

0.85

 this

0.83

 myself

0.83

 figuring

0.82

 yours

0.81

ya

0.81

 twitter

0.81

 yourselves

0.80

 THAT

0.78

it

0.77

Activations Density 0.543%

prepositions followed by abstract concepts or actions

prepositions and words indicating relationships or specifics about a topic

No Comments

No Known Activations