INDEX

Explanations

names of people or entities

oai_token-act-pair · gpt-3.5-turbo

specific names, brands, or entities mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 choke

-0.83

 bottleneck

-0.71

 gorilla

-0.70

 stripping

-0.70

 handc

-0.69

 striking

-0.68

ierrez

-0.68

 ______

-0.66

 brunt

-0.66

 disabled

-0.66

POSITIVE LOGITS

Politics

1.04

Daily

1.02

conom

0.98

 Magazine

0.97

Online

0.96

Media

0.95

Week

0.94

Blog

0.94

WN

0.94

NET

0.92

Activations Density 0.362%

names of people or entities

specific names, brands, or entities mentioned in the text

No Comments

No Known Activations