INDEX

Explanations

references to specific characters or titles, particularly related to entertainment such as movies or video games

oai_token-act-pair · gpt-3.5-turbo

titles and names of animated characters or franchises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ledged

-0.83

alty

-0.78

ickr

-0.73

 economically

-0.73

minist

-0.70

 volunteer

-0.70

uckland

-0.69

elled

-0.68

 institutional

-0.68

perm

-0.67

POSITIVE LOGITS

 Warrior

1.09

 Wars

1.08

 Universe

1.08

 Realms

1.07

 Breaker

1.04

 Fist

1.04

 Trigger

1.03

 Empires

1.01

 Ninja

1.00

 Girl

1.00

Activations Density 0.193%

references to specific characters or titles, particularly related to entertainment such as movies or video games

titles and names of animated characters or franchises

No Comments

No Known Activations