INDEX

Explanations

references to specific geographic locations, particularly related to politics and competition

oai_token-act-pair · gpt-3.5-turbo

terms related to geographical locations and contexts

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

rawdownloadcloneembedreportprint

-0.83

ascript

-0.73

Marginal

-0.70

acci

-0.69

umatic

-0.68

emonic

-0.68

romy

-0.67

Interstitial

-0.66

 clutch

-0.66

"]=>

-0.65

POSITIVE LOGITS

 Martha

0.82

 Amos

0.81

Wil

0.77

 Boris

0.76

 Alvin

0.76

 Judah

0.75

 William

0.75

Ben

0.75

 Pompe

0.75

 Shap

0.75

Activations Density 0.573%

references to specific geographic locations, particularly related to politics and competition

terms related to geographical locations and contexts

No Comments

No Known Activations