INDEX

Explanations

mentions of employees in a work context

oai_token-act-pair · gpt-3.5-turbo

mentions of "employees" or "employee" 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

 horr

-0.74

rous

-0.73

soon

-0.70

Pac

-0.68

 Cause

-0.68

COMPLE

-0.66

theless

-0.65

Brow

-0.65

las

-0.63

forward

-0.62

POSITIVE LOGITS

onomy

0.81

 cafeteria

0.79

 Employees

0.79

arers

0.78

 employees

0.73

 unions

0.73

 personnel

0.71

hips

0.71

illary

0.70

galitarian

0.69

Activations Density 0.033%

mentions of employees in a work context

mentions of "employees" or "employee" in various contexts

No Comments

No Known Activations