INDEX

Explanations

references to political entities, particularly governments

oai_token-act-pair · gpt-3.5-turbo

mentions of government entities and their actions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Ô

-0.75

Rank

-0.69

 Plaint

-0.69

 guiActiveUn

-0.67

 Loop

-0.67

 Fortune

-0.65

 Strip

-0.64

 Blazing

-0.64

Crime

-0.64

RANT

-0.63

POSITIVE LOGITS

 ministers

1.02

arians

0.93

MPs

0.89

 departments

0.84

 Ministers

0.84

 appoint

0.84

wide

0.83

 shutdown

0.82

 benches

0.82

 minister

0.81

Activations Density 0.068%

references to political entities, particularly governments

mentions of government entities and their actions

No Known Activations