INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

statements of ownership or the existence of places and properties

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

obin

-0.76

 impulses

-0.72

 warranties

-0.71

 tendencies

-0.69

 strokes

-0.68

know

-0.68

isms

-0.67

 critiques

-0.66

 explanations

-0.66

 pills

-0.66

POSITIVE LOGITS

 located

1.45

 situated

1.45

 Located

1.21

 housed

1.18

Located

1.13

 inhabited

1.13

 frequ

1.12

 staffed

1.10

 bustling

1.10

 adjacent

1.08

Activations Density 0.262%

locations or places

statements of ownership or the existence of places and properties

No Comments

No Known Activations