INDEX

Explanations

mentions of fan-related activities or works related to a specific topic

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "fan" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Johnston

-0.68

Alz

-0.64

 muddy

-0.64

apeake

-0.63

 Morning

-0.63

 Lans

-0.61

 Danger

-0.60

 Downs

-0.59

 Annotations

-0.59

 Aviv

-0.59

POSITIVE LOGITS

atical

1.57

atics

1.46

boys

1.39

fare

1.39

fiction

1.30

boy

1.28

atically

1.26

club

1.22

atic

1.22

ci

1.07

Activations Density 0.033%

mentions of fan-related activities or works related to a specific topic

occurrences of the word "fan" in various contexts

No Comments

No Known Activations