INDEX

Explanations

words related to careers or professional occupations

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the word "career" and related phrases

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bite

-0.73

 Lumpur

-0.71

armed

-0.69

borough

-0.68

burgh

-0.65

Ĩ

-0.65

UA

-0.64

 Morning

-0.62

akens

-0.62

legged

-0.61

POSITIVE LOGITS

 trajectory

1.07

 progression

0.88

 traject

0.88

 achievements

0.84

 advancement

0.84

 accomplishments

0.84

 aspirations

0.82

 Achievement

0.80

 spanning

0.80

 expectancy

0.79

Activations Density 0.033%

words related to careers or professional occupations

repeated mentions of the word "career" and related phrases

No Comments

No Known Activations