INDEX

Explanations

references to the science fiction franchise "Star Trek."

oai_token-act-pair · gpt-3.5-turbo

mentions of "Star Trek" and its associated titles or references

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

ividual

-0.82

 helicop

-0.74

-0.72

urers

-0.72

 reconc

-0.70

displayText

-0.68

anmar

-0.67

udic

-0.66

isters

-0.65

urer

-0.65

POSITIVE LOGITS

kies

1.18

kie

0.97

 Voyager

0.92

 Cruiser

0.86

 Expedition

0.84

 Enterprise

0.83

 Trek

0.83

kers

0.80

 Yamato

0.79

Movie

0.75

Activations Density 0.052%

references to the science fiction franchise "Star Trek."

mentions of "Star Trek" and its associated titles or references

No Comments

No Known Activations