INDEX

Explanations

phrases expressing comparison between two entities or events

oai_token-act-pair · gpt-3.5-turbo

conjunctions used to connect clauses or ideas in sentences

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

PLE

-0.65

ews

-0.65

renheit

-0.64

Fed

-0.61

ERN

-0.60

 Eternity

-0.59

Latest

-0.58

oos

-0.57

Adds

-0.56

 Prometheus

-0.55

POSITIVE LOGITS

sym

0.79

lear

0.70

ertodd

0.69

etheless

0.67

conservancy

0.66

ovember

0.64

DragonMagazine

0.63

++)

0.61

tti

0.59

isSpecialOrderable

0.58

Activations Density 0.691%

phrases expressing comparison between two entities or events

conjunctions used to connect clauses or ideas in sentences

No Comments

No Known Activations