INDEX

Explanations

phrases related to movies and entertainment sequels or continuations

oai_token-act-pair · gpt-3.5-turbo

elements related to television series, particularly those that feature new or recurring storylines and characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

à¼

-0.94

EPA

-0.85

HCR

-0.84

alde

-0.82

ï

-0.80

Figure

-0.79

Federal

-0.79

ogy

-0.78

fax

-0.77

externalActionCode

-0.76

POSITIVE LOGITS

 sequels

1.29

 flashbacks

1.25

 storylines

1.19

 villains

1.12

 characters

1.08

 vampires

1.06

 supernatural

1.03

 superheroes

1.02

 mutants

1.02

 collaborations

1.00

Activations Density 0.458%

phrases related to movies and entertainment sequels or continuations

elements related to television series, particularly those that feature new or recurring storylines and characters

No Comments

No Known Activations