INDEX

Explanations

tech-related terms and functions involving programming languages

oai_token-act-pair · gpt-3.5-turbo

symbols and special characters used in coding or programming contexts

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

ittal

-0.95

 thor

-0.79

ischer

-0.78

anging

-0.73

>[

-0.72

 babys

-0.72

 outl

-0.69

isch

-0.69

andre

-0.68

oubted

-0.67

POSITIVE LOGITS

 Enhancement

1.02

Premium

0.92

 Month

0.87

 Enhance

0.87

 Increases

0.86

 Modes

0.85

 Ratio

0.85

 Ages

0.84

 Groups

0.82

 Types

0.82

Activations Density 0.644%

tech-related terms and functions involving programming languages

symbols and special characters used in coding or programming contexts

No Comments

No Known Activations