INDEX

Explanations

words related to different television channels

oai_token-act-pair · gpt-3.5-turbo

mentions of television channels

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

arcity

-0.74

enty

-0.72

ever

-0.72

ĻĤ

-0.70

ggies

-0.70

 Oilers

-0.68

olding

-0.67

sson

-0.67

Reviewer

-0.67

iking

-0.66

POSITIVE LOGITS

 Channel

0.99

Channel

0.96

 Divinity

0.93

 Tunnel

0.86

 Islands

0.84

Mask

0.80

 channel

0.79

 Broadcasting

0.78

Sav

0.71

washing

0.70

Activations Density 0.011%

words related to different television channels

mentions of television channels

No Comments

No Known Activations