INDEX

Explanations

individuals or groups of people within a community

oai_token-act-pair · gpt-3.5-turbo

references to social groups and relationships

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

 Coch

-0.73

Osc

-0.71

©¶æ

-0.70

Vert

-0.63

 guiName

-0.63

 Stam

-0.61

 Toast

-0.60

 Auckland

-0.60

 spac

-0.60

 Startup

-0.60

POSITIVE LOGITS

 alike

1.99

 thereof

0.93

 respectively

0.78

conservancy

0.75

 abroad

0.74

 extraord

0.73

enei

0.71

estine

0.70

govtrack

0.67

 across

0.66

Activations Density 0.267%

individuals or groups of people within a community

references to social groups and relationships

No Comments

No Known Activations