INDEX

Explanations

references to political entities, specifically the term "Senate"

oai_token-act-pair · gpt-3.5-turbo

references to the Senate

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

resp

-0.67

Ub

-0.67

spr

-0.64

unks

-0.62

tru

-0.62

zsche

-0.62

ãĤ¨ãĥ«

-0.62

dx

-0.60

errilla

-0.59

tale

-0.59

POSITIVE LOGITS

 Judiciary

1.31

 Majority

1.27

 Appropriations

1.10

 Minority

1.06

 Chamber

1.01

 chamber

0.96

 filibuster

0.94

 Commerce

0.94

 Committee

0.93

 subcommittee

0.92

Activations Density 0.031%

references to political entities, specifically the term "Senate"

references to the Senate

No Comments

No Known Activations