INDEX

Explanations

URLs with the pattern "lexiecanne" and related keywords or phrases

oai_token-act-pair · gpt-3.5-turbo

references to specific entities, likely related to people, companies, or brands

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

cliffe

-0.70

kefeller

-0.66

bent

-0.64

yip

-0.63

erto

-0.61

FML

-0.59

coat

-0.58

ctl

-0.58

 robbers

-0.56

 soap

-0.56

POSITIVE LOGITS

uria

0.72

umeric

0.59

ioxide

0.57

rette

0.57

ãĤ¢

0.56

amiya

0.56

thirds

0.55

iffin

0.55

 Rails

0.55

ãĥī

0.54

Activations Density 0.351%

URLs with the pattern "lexiecanne" and related keywords or phrases

references to specific entities, likely related to people, companies, or brands

No Comments

No Known Activations