INDEX

Explanations

phrases mentioning "The Hollywood Reporter."

oai_token-act-pair · gpt-3.5-turbo

mentions of specific reporters and reporting entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

rams

-0.91

sur

-0.82

inst

-0.80

err

-0.78

chat

-0.73

rals

-0.72

sky

-0.72

BuyableInstoreAndOnline

-0.71

reek

-0.70

gone

-0.70

POSITIVE LOGITS

 Reporter

1.43

 Examiner

0.92

 Journalists

0.90

 Worker

0.84

 Investor

0.82

 Transcript

0.77

 Writer

0.77

 Weekly

0.76

 Digest

0.74

 Photographer

0.73

Activations Density 0.006%

phrases mentioning "The Hollywood Reporter."

mentions of specific reporters and reporting entities

No Comments

No Known Activations