INDEX

Explanations

phrases related to research or analysis

oai_token-act-pair · gpt-3.5-turbo

occurrences of the pronoun "We."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

quo

-0.62

 srfAttach

-0.61

 arises

-0.57

 bloc

-0.57

 fluids

-0.56

 manifests

-0.56

 totality

-0.55

~/.

-0.54

 parchment

-0.54

 disappears

-0.54

POSITIVE LOGITS

eks

1.40

alth

1.35

akening

1.35

ird

1.31

ighed

1.28

instein

1.26

ldon

1.14

bsite

1.12

igh

1.11

akens

1.10

Activations Density 0.125%

phrases related to research or analysis

occurrences of the pronoun "We."

No Comments

No Known Activations