INDEX

Explanations

references to workers in various contexts, such as productivity, accidents, and disputes

oai_token-act-pair · gpt-3.5-turbo

mentions of "worker" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

laus

-0.76

ories

-0.73

Viz

-0.72

 venerable

-0.71

hemy

-0.69

raints

-0.69

olic

-0.67

aber

-0.65

 sway

-0.65

 Drawn

-0.62

POSITIVE LOGITS

worker

1.07

 worker

1.00

 Worker

0.97

handler

0.83

 bees

0.82

ufact

0.80

geist

0.80

fare

0.78

 ants

0.76

bee

0.76

Activations Density 0.011%

references to workers in various contexts, such as productivity, accidents, and disputes

mentions of "worker" in various contexts

No Comments

No Known Activations