INDEX

Explanations

words related to job titles or positions of authority, specifically focusing on management roles

oai_token-act-pair · gpt-3.5-turbo

references to management 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

enegger

-0.98

âĦ¢:

-0.76

ead

-0.74

lihood

-0.70

Pac

-0.67

 Towns

-0.67

DonaldTrump

-0.66

tein

-0.65

 Bour

-0.64

sov

-0.63

POSITIVE LOGITS

management

0.96

Management

0.78

 management

0.77

 manag

0.77

 restructuring

0.76

 consultancy

0.76

ahime

0.75

 executives

0.75

 turnover

0.69

 secretaries

0.69

Activations Density 0.036%

words related to job titles or positions of authority, specifically focusing on management roles

references to management in various contexts

No Comments

No Known Activations