INDEX

Explanations

references to technical nodes or elements in a system

oai_token-act-pair · gpt-3.5-turbo

mentions of network nodes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

aternity

-0.87

rued

-0.79

quickShipAvailable

-0.76

soDeliveryDate

-0.73

letters

-0.73

stakes

-0.69

 Dragonbound

-0.66

frames

-0.66

 Gazette

-0.65

taking

-0.65

POSITIVE LOGITS

 node

1.42

 nodes

1.29

node

0.88

 Node

0.80

 guiActiveUn

0.76

Node

0.75

 cluster

0.75

 bottleneck

0.75

 pier

0.73

js

0.72

Activations Density 0.007%

references to technical nodes or elements in a system

mentions of network nodes

No Comments

No Known Activations