INDEX

Explanations

phrases related to the media and its actions

oai_token-act-pair · gpt-3.5-turbo

references to media treatment and portrayal of political issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mobility

-0.77

tein

-0.76

 Solitaire

-0.69

ozyg

-0.68

 exerc

-0.68

 repay

-0.67

 lottery

-0.65

EStreamFrame

-0.65

 Sacrifice

-0.65

 remission

-0.64

POSITIVE LOGITS

 portraying

0.86

 pundits

0.86

atters

0.83

orters

0.81

reporting

0.81

levision

0.81

 portrays

0.80

 broadcasting

0.80

 Hannity

0.80

 obsc

0.78

Activations Density 0.445%

phrases related to the media and its actions

references to media treatment and portrayal of political issues

No Comments

No Known Activations