INDEX

Explanations

phrases related to visual content or images

oai_token-act-pair · gpt-3.5-turbo

instances of information and data-related content

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etheless

-0.73

illard

-0.69

urther

-0.67

olyn

-0.63

 coupling

-0.62

 charism

-0.62

JV

-0.62

ymm

-0.61

ucky

-0.59

collection

-0.59

POSITIVE LOGITS

ynthesis

0.91

print

0.87

eval

0.73

urized

0.72

arial

0.71

bol

0.70

DragonMagazine

0.69

LAB

0.66

udic

0.63

urable

0.63

Activations Density 0.896%

phrases related to visual content or images

instances of information and data-related content

No Comments

No Known Activations