INDEX

Explanations

phrases related to educational activities

oai_token-act-pair · gpt-3.5-turbo

references to locations or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

OLOG

-0.81

Iterator

-0.80

Prosecut

-0.73

Accessory

-0.72

DragonMagazine

-0.71

-0.69

RG

-0.69

EVA

-0.67

OGR

-0.67

åŃ

-0.67

POSITIVE LOGITS

 whom

1.42

 distress

0.88

 alike

0.82

 accessing

0.80

 whose

0.77

 attendance

0.77

 afar

0.72

 discovering

0.70

 Plymouth

0.70

who

0.70

Activations Density 0.415%

phrases related to educational activities

references to locations or places

No Comments

No Known Activations