INDEX

Explanations

terms related to transparency and accountability in various contexts

oai_token-act-pair · gpt-3.5-turbo

concepts related to transparency and accountability

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

erville

-0.72

Interstitial

-0.71

anova

-0.65

iewicz

-0.63

skill

-0.63

HAM

-0.63

INGTON

-0.61

awar

-0.61

 Gohan

-0.61

aceous

-0.61

POSITIVE LOGITS

parency

0.95

recy

0.91

 disclosures

0.83

 disclosure

0.83

 transparency

0.81

 DeVos

0.78

 transparent

0.76

 Agenda

0.74

 Transparency

0.73

 Disclosure

0.72

Activations Density 0.038%

terms related to transparency and accountability in various contexts

concepts related to transparency and accountability

No Comments

No Known Activations