INDEX

Explanations

mentions of positions or titles such as "Deputy."

oai_token-act-pair · gpt-3.5-turbo

references to various levels of deputy positions in government

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

stakes

-0.82

ographed

-0.82

ograph

-0.81

pread

-0.80

ech

-0.77

ĸļ

-0.76

olen

-0.76

ologies

-0.75

yrs

-0.75

oven

-0.74

POSITIVE LOGITS

 sheriff

1.05

 chief

1.03

 sher

1.00

 director

1.00

 deputy

0.99

 mayor

0.99

 editor

0.98

 assistant

0.95

 secretary

0.93

 commander

0.93

Activations Density 0.024%

mentions of positions or titles such as "Deputy."

references to various levels of deputy positions in government

No Comments

No Known Activations