INDEX

Explanations

negations in sentences

oai_token-act-pair · gpt-3.5-turbo

negations or expressions that indicate the absence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

itiz

-0.77

 Laun

-0.70

PDATE

-0.69

Gry

-0.68

lined

-0.66

 Citiz

-0.63

 Seasons

-0.63

 Creative

-0.63

çĶŁ

-0.62

IGN

-0.62

POSITIVE LOGITS

 necessarily

1.24

 intend

1.13

 deserve

1.12

 belong

1.11

 exist

1.09

 bother

1.09

 seem

1.09

 condone

1.07

 know

1.07

 discriminate

1.01

Activations Density 0.108%

negations in sentences

negations or expressions that indicate the absence of something

No Comments

No Known Activations