INDEX

Explanations

programming-related terms, specifically focusing on arguments and parameters

oai_token-act-pair · gpt-3.5-turbo

technical terms related to arguments and parameters in programming

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

blogspot

-0.79

historic

-0.76

icult

-0.73

iful

-0.72

SEA

-0.71

iss

-0.70

opia

-0.69

 millenn

-0.68

oria

-0.67

Bench

-0.66

POSITIVE LOGITS

uments

1.06

 args

0.90

ument

0.89

 passed

0.86

 arguments

0.75

 packets

0.74

fet

0.74

 names

0.71

 slots

0.70

 supplied

0.70

Activations Density 0.034%

programming-related terms, specifically focusing on arguments and parameters

technical terms related to arguments and parameters in programming

No Comments

No Known Activations