INDEX

Explanations

references to specific news organizations and individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific organizations or entities, particularly in a news context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pering

-0.90

acters

-0.83

phas

-0.81

uring

-0.81

obi

-0.81

akable

-0.79

oller

-0.77

tha

-0.76

auga

-0.75

opher

-0.75

POSITIVE LOGITS

ND

0.84

 Seym

0.78

 Unicorn

0.67

ND

0.65

 Airport

0.62

ACP

0.62

Dil

0.61

 clearance

0.60

 Editors

0.59

 Fein

0.59

Activations Density 0.062%

references to specific news organizations and individuals

mentions of specific organizations or entities, particularly in a news context

No Comments

No Known Activations