INDEX

Explanations

phrases related to the Star Trek franchise

oai_token-act-pair · gpt-3.5-turbo

references to the Star Trek franchise

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

ividual

-0.91

 reconc

-0.75

ienced

-0.69

 brow

-0.68

aunder

-0.67

theless

-0.65

ebin

-0.64

essage

-0.63

iard

-0.63

 confir

-0.62

POSITIVE LOGITS

kies

1.12

 Voyager

0.95

 Expedition

0.92

 Enterprise

0.88

kie

0.86

 Cruiser

0.86

 Trek

0.86

Movie

0.85

 Starfleet

0.85

 Beyond

0.85

Activations Density 0.014%

phrases related to the Star Trek franchise

references to the Star Trek franchise

No Comments

No Known Activations