INDEX

Explanations

terms related to machine learning, computer programming, and technology

oai_token-act-pair · gpt-3.5-turbo

technical acronyms and coding languages relevant to software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

had

-0.81

ansas

-0.77

taboola

-0.76

ÃŃs

-0.71

fred

-0.70

Ê

-0.70

hra

-0.70

Ã³

-0.70

gal

-0.70

hig

-0.69

POSITIVE LOGITS

WARE

1.19

Enabled

0.88

 backend

0.87

 specification

0.86

atcher

0.86

etting

0.84

LOCK

0.84

Configuration

0.83

 compatibility

0.82

 compliant

0.82

Activations Density 0.147%

terms related to machine learning, computer programming, and technology

technical acronyms and coding languages relevant to software development

No Comments

No Known Activations