INDEX

Explanations

terms related to work-related activities or topics

oai_token-act-pair · gpt-3.5-turbo

phrases related to work and employment

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

onen

-0.80

vous

-0.79

threat

-0.73

å£«

-0.73

etus

-0.71

 mosqu

-0.71

dot

-0.70

vati

-0.68

vir

-0.68

 Typh

-0.67

POSITIVE LOGITS

 miracles

0.71

 Abbey

0.69

umen

0.66

 briefs

0.65

DVD

0.64

 Engels

0.62

 faculty

0.61

 ethic

0.61

 capacity

0.60

 expended

0.59

Activations Density 0.417%

terms related to work-related activities or topics

phrases related to work and employment

No Comments

No Known Activations