INDEX

Explanations

specific mentions of "House Speaker" in political contexts

oai_token-act-pair · gpt-3.5-turbo

references to the U.S. House of Representatives and its members

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

zsche

-0.80

istically

-0.80

arre

-0.69

ilitary

-0.68

...]

-0.66

atra

-0.65

ï¸ı

-0.65

 internationally

-0.64

umbai

-0.64

estamp

-0.63

POSITIVE LOGITS

 Speaker

1.22

 Judiciary

1.18

 Ways

1.15

 Oversight

1.13

 Appropriations

1.12

 Majority

1.06

 Republicans

1.04

GOP

1.04

wives

0.98

 Minority

0.97

Activations Density 0.032%

specific mentions of "House Speaker" in political contexts

references to the U.S. House of Representatives and its members

No Comments

No Known Activations