INDEX

Explanations

key terms related to programming languages and paradigms, particularly focusing on functional programming

oai_token-act-pair · gpt-3.5-turbo

references to programming languages and paradigms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.92

ãĥĩãĤ£

-0.72

adal

-0.69

EStream

-0.65

tre

-0.65

å¥³

-0.63

scl

-0.63

 Dish

-0.62

lie

-0.62

soType

-0.62

POSITIVE LOGITS

 abstraction

0.91

 library

0.89

 Architecture

0.88

 implementations

0.87

matically

0.86

 APIs

0.86

ojure

0.85

 Clojure

0.85

 concepts

0.84

 Haskell

0.84

Activations Density 0.179%

key terms related to programming languages and paradigms, particularly focusing on functional programming

references to programming languages and paradigms

No Comments

No Known Activations