INDEX

Explanations

words or phrases related to activation processes

oai_token-act-pair · gpt-3.5-turbo

terms related to activation processes and triggers

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

esan

-0.77

 Abram

-0.68

apest

-0.67

umbo

-0.67

 Hague

-0.64

elf

-0.64

ago

-0.62

 Tale

-0.62

 Apost

-0.62

 Norman

-0.62

POSITIVE LOGITS

 activation

1.01

 activated

0.89

 charcoal

0.84

 activate

0.84

activation

0.83

activated

0.82

 activating

0.81

 activates

0.81

 activ

0.80

uates

0.74

Activations Density 0.015%

words or phrases related to activation processes

terms related to activation processes and triggers

No Known Activations