INDEX

Explanations

words related to technology and specifications, particularly focusing on the term 'dual'

oai_token-act-pair · gpt-3.5-turbo

references to dual functionality or dual systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

FORE

-0.79

otle

-0.75

UFF

-0.74

uden

-0.71

 Warehouse

-0.70

 Lans

-0.68

andise

-0.67

akeru

-0.66

 Yards

-0.66

âĸĪâĸĪ

-0.65

POSITIVE LOGITS

fold

0.96

 simultaneous

0.87

ples

0.86

ities

0.85

ity

0.83

edged

0.82

 thirds

0.79

 sided

0.77

ieth

0.74

 nationals

0.73

Activations Density 0.016%

words related to technology and specifications, particularly focusing on the term 'dual'

references to dual functionality or dual systems

No Comments

No Known Activations