INDEX

Explanations

instances of the word "we" used at the beginning of sentences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "we" and its variations, indicating a focus on collective action or statements

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

forms

-0.77

 flows

-0.63

ãĤ¯

-0.60

REDACTED

-0.59

ses

-0.58

~/.

-0.57

imum

-0.56

 embod

-0.56

cum

-0.55

 guiActiveUnfocused

-0.55

POSITIVE LOGITS

're

1.11

athered

1.09

asel

1.07

eks

1.06

ibo

1.06

've

1.06

 wondered

1.04

arers

1.03

'll

1.03

akening

1.01

Activations Density 0.185%

instances of the word "we" used at the beginning of sentences

occurrences of the word "we" and its variations, indicating a focus on collective action or statements

No Comments

No Known Activations