INDEX

Explanations

specific numerical figures along with their associated words or phrases

oai_token-act-pair · gpt-3.5-turbo

references to time periods and their duration in descriptions of events or projects

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

isky

-0.67

 TEAM

-0.67

oided

-0.66

ifa

-0.64

zos

-0.63

raid

-0.62

estern

-0.61

GROUP

-0.61

atti

-0.60

 Interview

-0.60

POSITIVE LOGITS

 relevance

1.05

 significance

1.01

 validity

1.00

 existed

0.98

 usefulness

0.93

 exist

0.90

 occurring

0.90

 meaning

0.89

 effectiveness

0.88

 origin

0.88

Activations Density 0.859%

specific numerical figures along with their associated words or phrases

references to time periods and their duration in descriptions of events or projects

No Comments

No Known Activations