INDEX

Explanations

sentences that start with "we."

oai_token-act-pair · gpt-3.5-turbo

the word "We" to indicate collective actions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mehran

-0.69

 guiActiveUnfocused

-0.64

cum

-0.63

SPONSORED

-0.62

 PUBLIC

-0.59

 totality

-0.59

 steroids

-0.59

 Publication

-0.57

uates

-0.57

LSD

-0.57

POSITIVE LOGITS

've

1.15

're

1.10

'll

1.07

ldon

1.05

bley

0.99

akening

0.99

ighed

0.99

eping

0.98

selves

0.94

alth

0.93

Activations Density 0.168%

sentences that start with "we."

the word "We" to indicate collective actions or statements

No Comments

No Known Activations