INDEX

Explanations

words related to specific job duties or workforce management

oai_token-act-pair · gpt-3.5-turbo

phrases indicating responsibility or accountability in high-pressure contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ilion

-0.98

unctions

-0.73

enture

-0.72

 unbeliev

-0.71

akura

-0.71

urous

-0.71

oppable

-0.70

thumbnails

-0.69

udi

-0.69

inent

-0.69

POSITIVE LOGITS

 Acquisition

0.68

 Seeking

0.66

 Saving

0.66

---------

0.64

sid

0.64

 Aless

0.64

 cigars

0.63

 Herald

0.62

 Rail

0.62

 Alive

0.61

Activations Density 0.000%

words related to specific job duties or workforce management

phrases indicating responsibility or accountability in high-pressure contexts

No Comments

No Known Activations