INDEX

Explanations

dates and locations related to where speeches were given

oai_token-act-pair · gpt-3.5-turbo

references to speeches and public addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nah

-0.85

usercontent

-0.85

 glitch

-0.75

 workaround

-0.73

 mustard

-0.71

 ILCS

-0.70

 discovered

-0.69

chrome

-0.68

 smugglers

-0.67

 churn

-0.66

POSITIVE LOGITS

 keynote

0.93

 podium

0.88

 televised

0.87

 commencement

0.86

TED

0.82

posium

0.81

CES

0.79

 attendees

0.79

Interstitial

0.76

 aloud

0.76

Activations Density 0.277%

dates and locations related to where speeches were given

references to speeches and public addresses

No Comments

No Known Activations