INDEX

Explanations

references to arrays and their operations

oai_token-act-pair · gpt-3.5-turbo

terms related to arrays 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

å§«

-0.86

psey

-0.84

blems

-0.80

laus

-0.74

é¾įå¥ĳå£«

-0.73

insula

-0.70

peria

-0.67

undai

-0.66

enthal

-0.65

ggles

-0.65

POSITIVE LOGITS

Buffer

0.98

ptr

0.80

array

0.73

dump

0.72

buf

0.71

 subscript

0.70

([

0.70

Object

0.70

 separ

0.69

 container

0.69

Activations Density 0.024%

references to arrays and their operations

terms related to arrays in programming

No Comments

No Known Activations