INDEX

Explanations

tech-related terms and brands

oai_token-act-pair · gpt-3.5-turbo

terms related to technology and software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 carbohyd

-0.77

bered

-0.72

 eaten

-0.71

pherd

-0.68

 numbered

-0.68

pard

-0.67

angered

-0.65

 nineteen

-0.64

 wast

-0.64

 slaughtered

-0.64

POSITIVE LOGITS

Tools

1.25

Tool

1.07

Cache

1.05

 Labs

1.03

Plugin

1.03

Safe

1.01

Works

1.01

Widget

1.01

Shop

1.00

JS

1.00

Activations Density 0.302%

tech-related terms and brands

terms related to technology and software

No Comments

No Known Activations