INDEX

Explanations

proper nouns and descriptions related to images or photographs

oai_token-act-pair · gpt-3.5-turbo

references to photography or images in the text

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

Hof

-0.77

Kir

-0.76

bush

-0.71

hom

-0.70

Hom

-0.68

gor

-0.68

andal

-0.67

 Palest

-0.67

Oro

-0.67

gor

-0.66

POSITIVE LOGITS

Pwr

0.75

zeb

0.72

OURCE

0.72

taboola

0.72

QC

0.71

seq

0.70

submit

0.70

 Citation

0.68

ogue

0.68

ptions

0.67

Activations Density 0.333%

proper nouns and descriptions related to images or photographs

references to photography or images in the text

No Comments

No Known Activations