INDEX

Explanations

phrases related to specific aspects or elements being highlighted or discussed

oai_token-act-pair · gpt-3.5-turbo

phrases related to identifying specific parts of experiences or narratives

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Klux

-0.74

apons

-0.74

iko

-0.68

 sidx

-0.68

 practition

-0.68

flat

-0.68

stable

-0.67

intent

-0.67

irrel

-0.65

avascript

-0.64

POSITIVE LOGITS

ially

0.83

ials

0.76

udes

0.69

 Darrell

0.68

 Hannity

0.67

Hoo

0.66

iest

0.66

uary

0.65

(>

0.63

Suz

0.63

Activations Density 0.044%

phrases related to specific aspects or elements being highlighted or discussed

phrases related to identifying specific parts of experiences or narratives

No Comments

No Known Activations