INDEX

Explanations

different types of professionals within various industries

oai_token-act-pair · gpt-3.5-turbo

references to various roles in professional and academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Bung

-0.71

Reloaded

-0.71

icity

-0.66

tein

-0.64

 Horizon

-0.63

Veh

-0.63

Lov

-0.62

 Auckland

-0.62

oret

-0.61

 spac

-0.60

POSITIVE LOGITS

 alike

2.52

 respectively

0.99

 thereof

0.84

 worldwide

0.81

who

0.80

 interested

0.79

 eager

0.77

 vying

0.75

 everywhere

0.73

 wishing

0.73

Activations Density 0.245%

different types of professionals within various industries

references to various roles in professional and academic contexts

No Comments

No Known Activations