INDEX

Explanations

mentions of the word "Ghost"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Ghost."

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

NRS

-0.77

erity

-0.77

unes

-0.76

enegger

-0.74

ECA

-0.72

onian

-0.72

tical

-0.71

itia

-0.69

×Ĳ

-0.69

tics

-0.69

POSITIVE LOGITS

busters

1.07

writer

0.99

buster

0.91

writing

0.91

written

0.89

glass

0.86

 haunting

0.82

door

0.82

writers

0.81

ghost

0.80

Activations Density 0.020%

mentions of the word "Ghost"

mentions of the word "Ghost."

No Comments

No Known Activations