INDEX

Explanations

phrases related to ambition or striving towards a goal

oai_token-act-pair · gpt-3.5-turbo

words related to aspirations and ambitions

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

rooms

-0.75

picking

-0.72

waves

-0.72

bah

-0.70

ockets

-0.66

orders

-0.66

avis

-0.65

gren

-0.64

anas

-0.64

phone

-0.64

POSITIVE LOGITS

 aspire

1.09

 ambition

1.01

 aspirations

0.99

 aspiration

0.97

 ambitions

0.94

 attainment

0.93

pires

0.86

bitious

0.84

 ambitious

0.81

 lofty

0.81

Activations Density 0.054%

phrases related to ambition or striving towards a goal

words related to aspirations and ambitions

No Comments

No Known Activations