INDEX

Explanations

programming-related terms and commands in C and Python

oai_token-act-pair · gpt-3.5-turbo

references to programming functions and their attributes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Brexit

-0.79

Scotland

-0.75

chu

-0.73

ãĥ»

-0.71

Â½

-0.71

Advertisement

-0.71

å·

-0.70

bill

-0.70

Tube

-0.70

POSITIVE LOGITS

 compiler

1.22

 parser

1.17

 debugger

1.16

 simplest

1.15

 default

1.11

 following

1.11

 underlying

1.08

 executable

1.07

 constructor

1.05

 runtime

1.05

Activations Density 0.186%

programming-related terms and commands in C and Python

references to programming functions and their attributes

No Comments

No Known Activations