INDEX

Explanations

the word "Thor" along with associated contexts or mentions

oai_token-act-pair · gpt-3.5-turbo

references to the character Thor from mythology and comics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ilies

-0.74

icals

-0.73

istas

-0.71

ello

-0.68

astery

-0.67

 gardens

-0.65

esan

-0.64

caf

-0.63

ggies

-0.63

 disp

-0.62

POSITIVE LOGITS

 Thor

3.89

Thor

3.16

 thor

1.89

 Loki

1.72

 Asgard

1.71

 Odin

1.53

 Ragnarok

1.39

 Ragnar

1.38

 Hulk

1.26

 Avengers

1.26

Activations Density 0.010%

the word "Thor" along with associated contexts or mentions

references to the character Thor from mythology and comics

No Comments

No Known Activations