INDEX

Explanations

prepositions 'in' when accompanied by a location or action described after it

oai_token-act-pair · gpt-3.5-turbo

the word "in" used 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

llor

-0.89

 incumb

-0.76

NOW

-0.73

CLASSIFIED

-0.73

 endors

-0.71

cia

-0.65

HAEL

-0.63

 Insider

-0.62

 appoint

-0.61

leans

-0.61

POSITIVE LOGITS

 lieu

1.29

 accordance

1.16

 vitro

1.14

animate

1.13

 unison

1.12

between

1.12

 front

1.11

 spite

1.10

efficiency

1.07

 conjunction

1.06

Activations Density 0.489%

prepositions 'in' when accompanied by a location or action described after it

the word "in" used in various contexts

No Comments

No Known Activations