INDEX

Explanations

words related to things or activities being done with effort or force, such as "trying", "training", "tracking"

oai_token-act-pair · gpt-3.5-turbo

instances of the substring "tr."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ELS

-0.85

LEY

-0.74

 Mechdragon

-0.72

ãģ®éŃĶ

-0.70

æĸ¹

-0.69

WARE

-0.68

eers

-0.67

ELD

-0.66

MODE

-0.66

ARDS

-0.65

POSITIVE LOGITS

umps

1.30

ainer

1.17

acer

1.11

unks

1.08

usted

1.08

iceps

1.05

ained

1.04

ains

1.02

icol

1.02

amm

1.02

Activations Density 0.009%

words related to things or activities being done with effort or force, such as "trying", "training", "tracking"

instances of the substring "tr."

No Comments

No Known Activations