INDEX

Explanations

code snippets and technical terms related to programming functions and errors

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to exceptions and error handling in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

SPONSORED

-0.79

tumblr

-0.78

 whistlebl

-0.74

é¾

-0.73

 therap

-0.72

é¾įå

-0.72

clerosis

-0.72

âĢİ

-0.71

 Hobby

-0.71

stre

-0.71

POSITIVE LOGITS

 specified

1.19

 computed

1.07

 recursive

1.05

 integer

1.05

 lookup

1.00

 JSON

1.00

 Python

1.00

 parsed

0.99

 parameter

0.98

 default

0.97

Activations Density 0.761%

code snippets and technical terms related to programming functions and errors

terms and phrases related to exceptions and error handling in programming

No Comments

No Known Activations