INDEX

Explanations

code snippets and programming language syntax related to JavaScript and MongoDB

oai_token-act-pair · gpt-3.5-turbo

patterns related to programming syntax and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iple

-0.97

hyde

-0.92

alach

-0.90

ortal

-0.84

ipel

-0.79

etsk

-0.78

vae

-0.76

umen

-0.75

laus

-0.73

uum

-0.73

POSITIVE LOGITS

{"

0.85

({

0.78

[];

0.78

nil

0.76

 Mandatory

0.69

{}

0.68

 println

0.68

 Array

0.67

 Ùħ

0.67

{:

0.65

Activations Density 0.008%

code snippets and programming language syntax related to JavaScript and MongoDB

patterns related to programming syntax and function definitions

No Comments

No Known Activations