INDEX

Explanations

references to the word "ghost."

oai_token-act-pair · gpt-3.5-turbo

references to "Ghost" or "ghost" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

NRS

-0.78

erity

-0.76

tics

-0.73

utics

-0.70

thritis

-0.70

UTERS

-0.69

enegger

-0.69

oulos

-0.69

tical

-0.68

unes

-0.67

POSITIVE LOGITS

busters

1.03

writer

0.93

written

0.91

buster

0.91

 haunting

0.85

writing

0.85

glass

0.79

door

0.79

writers

0.76

 Recon

0.76

Activations Density 0.034%

references to the word "ghost."

references to "Ghost" or "ghost" in various contexts

No Comments

No Known Activations