INDEX

Explanations

mentions of political figures and leaders

oai_token-act-pair · gpt-3.5-turbo

the word "and" in conjunction with political figures and their affiliations or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

aves

-0.80

mol

-0.79

 mats

-0.73

 dunno

-0.70

xp

-0.70

Blocks

-0.70

paces

-0.70

ãĤ¤ãĥĪ

-0.68

onica

-0.67

moil

-0.66

POSITIVE LOGITS

 Chancellor

1.22

 Cabinet

1.20

 Vice

1.19

 Treasurer

1.17

 Congress

1.13

 Governor

1.12

 Secretary

1.11

 President

1.09

 Presidents

1.04

 chancellor

1.04

Activations Density 0.187%

mentions of political figures and leaders

the word "and" in conjunction with political figures and their affiliations or actions

No Comments

No Known Activations