INDEX

Explanations

prepositions indicating location or relationship between objects or ideas

oai_token-act-pair · gpt-3.5-turbo

phrases that include the preposition "in" indicating a location or context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 accordingly

-0.90

ãĤĬ

-0.82

press

-0.74

 PLEASE

-0.68

.$

-0.68

ctive

-0.65

Published

-0.65

icipated

-0.64

Assistant

-0.64

 furthermore

-0.63

POSITIVE LOGITS

 previous

1.34

 other

1.02

 earlier

0.93

 past

0.90

 predecessors

0.90

 neighbouring

0.88

 preceding

0.88

 neighboring

0.88

 elsewhere

0.88

 prior

0.87

Activations Density 0.175%

prepositions indicating location or relationship between objects or ideas

phrases that include the preposition "in" indicating a location or context

No Comments

No Known Activations