INDEX

Explanations

words related to media, technology, and business deals

oai_token-act-pair · gpt-3.5-turbo

terms related to media content and distribution

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

 adjourn

-0.76

ACTED

-0.70

akura

-0.69

natureconservancy

-0.69

 Juven

-0.67

sent

-0.66

eenth

-0.65

ĻĤ

-0.63

lied

-0.62

reath

-0.61

POSITIVE LOGITS

 royalties

0.78

netflix

0.78

 capabilities

0.73

 technologies

0.69

 activ

0.68

grass

0.68

 Everywhere

0.67

 Mehran

0.67

 Canaveral

0.66

 capacities

0.66

Activations Density 0.649%

words related to media, technology, and business deals

terms related to media content and distribution

No Comments

No Known Activations