INDEX

Explanations

information related to the search engine "Google"

oai_token-act-pair · gpt-3.5-turbo

references to the search engine Google

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

mble

-0.87

sole

-0.74

Sov

-0.72

rone

-0.70

OHN

-0.70

alid

-0.67

quez

-0.67

ework

-0.65

Sov

-0.63

ivari

-0.63

POSITIVE LOGITS

plex

0.92

 Scholar

0.90

 google

0.79

 searches

0.79

usercontent

0.75

 Doodle

0.72

vine

0.72

 sear

0.71

google

0.70

geist

0.69

Activations Density 0.018%

information related to the search engine "Google"

references to the search engine Google

No Comments

No Known Activations