INDEX

Explanations

mentions of dates and names

oai_token-act-pair · gpt-3.5-turbo

topics related to serious events or significant issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hiba

-0.79

conservancy

-0.79

independence

-0.74

ratulations

-0.70

interstitial

-0.66

packing

-0.64

 substit

-0.61

acc

-0.61

coord

-0.58

Charges

-0.57

POSITIVE LOGITS

 understatement

0.68

Wee

0.64

 gmaxwell

0.64

 Millenn

0.62

ombat

0.61

 Opinion

0.60

 commenter

0.60

 newsp

0.59

Klu

0.59

Activations Density 0.168%

mentions of dates and names

topics related to serious events or significant issues

No Comments

No Known Activations