INDEX

Explanations

phrases related to influencing or manipulating a situation or person

oai_token-act-pair · gpt-3.5-turbo

the word "into" in various contexts

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

hop

-0.85

zai

-0.84

thora

-0.68

 mathemat

-0.67

entimes

-0.66

anooga

-0.64

chin

-0.63

ancies

-0.62

ice

-0.61

chu

-0.60

POSITIVE LOGITS

 adulthood

0.99

 existence

0.83

 infinity

0.82

ournal

0.67

ob

0.67

 orbit

0.67

 eternity

0.64

 submission

0.63

 Isles

0.62

qqa

0.61

Activations Density 0.076%

phrases related to influencing or manipulating a situation or person

the word "into" in various contexts

No Comments

No Known Activations