INDEX

Explanations

names of characters and potentially places in a story

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of characters

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 confir

-0.83

 Accessed

-0.76

 Qualcomm

-0.70

 credential

-0.70

 EDITION

-0.68

 merit

-0.68

 telecommunications

-0.67

 deregulation

-0.65

 wastewater

-0.65

 industrial

-0.65

POSITIVE LOGITS

 Weasley

0.87

ilda

0.84

wen

0.83

 Tooth

0.81

abeth

0.78

hide

0.78

essa

0.77

 Noir

0.77

beard

0.76

 herself

0.76

Activations Density 0.460%

names of characters and potentially places in a story

proper nouns, specifically names of characters

No Comments

No Known Activations