INDEX

Explanations

words related to factors, influences, and procedures in a detailed context

oai_token-act-pair · gpt-3.5-turbo

conjunctions and modifiers within sentences

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

nee

-0.75

wife

-0.74

 Skydragon

-0.71

 Blazing

-0.68

ONSORED

-0.68

agle

-0.68

ager

-0.68

erker

-0.67

wreck

-0.67

ÃŃs

-0.65

POSITIVE LOGITS

 timelines

1.02

 personalities

0.99

 perspectives

0.98

 behaviors

0.94

 philosophies

0.93

 behaviours

0.91

 expressions

0.87

 vulnerabilities

0.87

 histories

0.87

 motivations

0.85

Activations Density 0.249%

words related to factors, influences, and procedures in a detailed context

conjunctions and modifiers within sentences

No Comments

No Known Activations