INDEX

Explanations

positive descriptive words

oai_token-act-pair · gpt-3.5-turbo

specific terms and concepts related to social and political issues

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

 Citation

-0.64

ĸļ

-0.59

 Telegram

-0.58

 CNBC

-0.57

odcast

-0.57

 Marketplace

-0.56

 Identified

-0.56

 Investor

-0.55

 LORD

-0.54

NPR

-0.54

POSITIVE LOGITS

related

0.76

 entries

0.75

 endorsements

0.73

 equivalents

0.73

 goodies

0.73

 activ

0.70

plet

0.69

 fodder

0.67

 sightings

0.66

pees

0.66

Activations Density 0.828%

positive descriptive words

specific terms and concepts related to social and political issues

No Comments

No Known Activations