INDEX

Explanations

words related to proper nouns or specific names

oai_token-act-pair · gpt-3.5-turbo

capital letters, specifically initials or names likely associated with titles or important terms

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

è£ħ

-0.62

REDACTED

-0.60

DOE

-0.59

stellar

-0.58

DragonMagazine

-0.58

hua

-0.57

 Bayer

-0.57

CBC

-0.56

ESV

-0.55

éĹĺ

-0.54

POSITIVE LOGITS

ombat

0.93

asses

0.88

umps

0.85

ifter

0.84

oots

0.83

elt

0.78

igg

0.78

ormon

0.78

oot

0.78

eret

0.77

Activations Density 0.187%

words related to proper nouns or specific names

capital letters, specifically initials or names likely associated with titles or important terms

No Comments

No Known Activations