INDEX

Explanations

verbs related to the action of looking at something intensely or for a long period of time

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "stare" in various forms and contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cial

-0.71

accompan

-0.68

Chel

-0.63

quet

-0.63

FER

-0.62

VEN

-0.62

Organ

-0.62

afort

-0.61

notes

-0.61

ELS

-0.60

POSITIVE LOGITS

dag

1.11

 blank

1.02

 attent

1.00

 helpless

0.89

 sideways

0.85

 unfocused

0.83

 gaze

0.82

 incred

0.82

 stares

0.80

 challeng

0.80

Activations Density 0.068%

verbs related to the action of looking at something intensely or for a long period of time

instances of the verb "stare" in various forms and contexts

No Comments

No Known Activations