INDEX

Explanations

names of individuals or entities, potentially related to politics or business

oai_token-act-pair · gpt-3.5-turbo

references to specific brands, models, and notable individuals

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

tein

-0.78

ruary

-0.61

ktop

-0.58

quest

-0.57

 reins

-0.54

 shove

-0.53

entimes

-0.52

 exped

-0.51

WAYS

-0.50

 defence

-0.49

POSITIVE LOGITS

 guiActiveUnfocused

0.75

 Clouds

0.62

weapons

0.62

BIL

0.59

ciating

0.59

henko

0.59

aic

0.59

zona

0.58

ucci

0.57

ova

0.57

Activations Density 1.202%

names of individuals or entities, potentially related to politics or business

references to specific brands, models, and notable individuals

No Comments

No Known Activations