INDEX

Explanations

proper nouns that are most likely locations or names of people

oai_token-act-pair · gpt-3.5-turbo

unique place names or geographic identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ailability

-0.66

 conduc

-0.66

 carbohyd

-0.63

 surv

-0.60

 Surviv

-0.59

¥ŀ

-0.59

ãĤ¨

-0.57

 gobl

-0.57

 conclud

-0.54

 adoptive

-0.54

POSITIVE LOGITS

 Creek

0.73

ville

0.72

ja

0.71

 Canyon

0.71

 Industries

0.71

 Brothers

0.70

 Junction

0.69

osaurus

0.68

 County

0.67

çĶ°

0.66

Activations Density 0.438%

proper nouns that are most likely locations or names of people

unique place names or geographic identifiers

No Comments

No Known Activations