INDEX

Explanations

proper nouns related to characters in movies or other fictional media

oai_token-act-pair · gpt-3.5-turbo

the word "in" and its frequent occurrences 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

jri

-0.73

$$$$

-0.73

incial

-0.73

ratulations

-0.72

isan

-0.71

llor

-0.70

 clust

-0.68

 incumb

-0.66

 landlords

-0.65

ollah

-0.65

POSITIVE LOGITS

verted

1.03

 Episode

1.02

 disguise

1.00

animate

0.99

 lieu

0.98

 Ghostbusters

0.96

 Mortal

0.96

 flashbacks

0.93

 Fantastic

0.92

 spite

0.88

Activations Density 0.168%

proper nouns related to characters in movies or other fictional media

the word "in" and its frequent occurrences in various contexts

No Comments

No Known Activations