INDEX

Explanations

pronouns referring to oneself or direct goals

oai_token-act-pair · gpt-3.5-turbo

the pronoun "it" used in varying contexts throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

undy

-0.71

und

-0.71

priv

-0.69

 Manufact

-0.67

=>

-0.66

inqu

-0.65

ixt

-0.64

hitting

-0.62

Gender

-0.62

Gene

-0.62

POSITIVE LOGITS

 nonetheless

1.44

 nevertheless

1.41

ain

1.09

 still

1.09

 certainly

1.08

'll

1.07

 shouldn

1.06

 doesn

1.05

 didn

1.05

 does

1.02

Activations Density 0.165%

pronouns referring to oneself or direct goals

the pronoun "it" used in varying contexts throughout the text

No Comments

No Known Activations