INDEX

Explanations

references to news articles or journalism entities, particularly "The Washington Post"

oai_token-act-pair · gpt-3.5-turbo

references to specific news publications

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

actionDate

-0.84

sed

-0.80

ardless

-0.74

depend

-0.74

ologically

-0.69

cles

-0.69

cling

-0.67

lua

-0.67

rising

-0.67

dependent

-0.65

POSITIVE LOGITS

 Magazine

1.02

 Digest

0.92

 Editorial

0.88

 bestselling

0.84

 Publishing

0.84

 Archive

0.82

 columnist

0.81

Magazine

0.80

 headlined

0.77

 Gazette

0.77

Activations Density 0.051%

references to news articles or journalism entities, particularly "The Washington Post"

references to specific news publications

No Comments

No Known Activations