INDEX

Explanations

words ending in 'ern'

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names or entities

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

 trickle

-0.70

 subsid

-0.64

 bout

-0.64

tin

-0.63

 Gamble

-0.63

 marrow

-0.63

 bluff

-0.60

EVs

-0.59

escal

-0.58

Arcade

-0.58

POSITIVE LOGITS

acle

1.19

acles

1.08

atural

1.06

esis

1.00

auts

0.99

sburg

0.95

acular

0.95

icus

0.93

igans

0.93

esse

0.91

Activations Density 0.025%

words ending in 'ern'

mentions of specific names or entities

No Comments

No Known Activations