INDEX

Explanations

terms related to methods or ways of doing things

oai_token-act-pair · gpt-3.5-turbo

references to various methods or methodologies

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

 impression

-0.66

 gloom

-0.65

 juven

-0.60

 earnest

-0.60

ternity

-0.60

 Sons

-0.59

 challeng

-0.59

igi

-0.59

 Childhood

-0.57

 Barkley

-0.57

POSITIVE LOGITS

ologies

1.79

ologically

1.31

ology

1.21

ologic

1.21

ical

1.18

ically

1.10

OLOGY

1.07

ologists

0.99

ological

0.99

ologist

0.98

Activations Density 0.032%

terms related to methods or ways of doing things

references to various methods or methodologies

No Comments

No Known Activations