INDEX

Explanations

terms related to neural networks

oai_token-act-pair · gpt-3.5-turbo

terms related to neural networks and neural activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

UID

-0.80

ARDS

-0.77

gerald

-0.72

UAL

-0.71

 Mankind

-0.69

Hispanic

-0.67

 Christy

-0.67

 Rabb

-0.66

edited

-0.64

alos

-0.64

POSITIVE LOGITS

 neural

1.12

 neur

0.96

 impulses

0.93

 implants

0.93

 muscles

0.86

 neurons

0.86

 activation

0.85

 circuitry

0.85

iac

0.85

 implant

0.83

Activations Density 0.006%

terms related to neural networks

terms related to neural networks and neural activity

No Comments

No Known Activations