INDEX

Explanations

people's names followed by verbs indicating what they said or did

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the."

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

thood

-0.86

pai

-0.73

adesh

-0.73

FIELD

-0.70

Solution

-0.69

arettes

-0.69

obyl

-0.67

ature

-0.67

iances

-0.66

aceae

-0.64

POSITIVE LOGITS

 Associated

1.12

BBC

1.08

 Guardian

1.07

 Huffington

1.03

 interviewer

1.01

 Daily

0.96

 newspaper

0.96

 Chronicle

0.94

 audience

0.94

 Observer

0.94

Activations Density 0.079%

people's names followed by verbs indicating what they said or did

instances of the word "the."

No Comments

No Known Activations