INDEX

Explanations

references to impeachment

oai_token-act-pair · gpt-3.5-turbo

terms related to the process of impeachment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Jacobs

-0.72

 Ideal

-0.70

 Vegan

-0.70

CHO

-0.69

 Desert

-0.68

 Clinic

-0.66

 Helmet

-0.66

anas

-0.64

Ðº

-0.64

 Wildcats

-0.63

POSITIVE LOGITS

 impe

3.04

 impeachment

2.14

ulp

1.86

onge

1.51

lik

1.12

lest

1.06

Hig

1.00

mov

0.99

elligence

0.87

 lewd

0.86

Activations Density 0.046%

references to impeachment

terms related to the process of impeachment

No Comments

No Known Activations