INDEX

Explanations

informative statements or explanations

oai_token-act-pair · gpt-3.5-turbo

verbs and phrases indicating the provision of information or summaries

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Initialized

-0.77

azo

-0.76

doms

-0.72

mare

-0.68

assault

-0.68

psc

-0.66

LINE

-0.64

amphetamine

-0.64

AME

-0.64

ahu

-0.63

POSITIVE LOGITS

 examples

1.24

 insights

1.16

 insight

1.12

 explanations

1.11

 detailed

1.09

 links

1.07

 insightful

1.03

 concise

1.03

 pointers

1.03

 descriptions

1.02

Activations Density 0.246%

informative statements or explanations

verbs and phrases indicating the provision of information or summaries

No Comments

No Known Activations