INDEX

Explanations

references to acts that are enjoyable or satisfying

oai_token-act-pair · gpt-3.5-turbo

terms related to requests and written documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

theless

-0.76

 Macedonia

-0.68

 railway

-0.67

 Railway

-0.66

 Brigade

-0.65

 brigade

-0.64

 squadron

-0.63

 Leone

-0.63

 calculus

-0.62

 translator

-0.62

POSITIVE LOGITS

urable

1.17

ured

1.11

enced

1.10

urers

1.07

encer

1.04

ures

1.04

eland

1.01

emet

1.00

iced

0.97

urally

0.97

Activations Density 0.026%

references to acts that are enjoyable or satisfying

terms related to requests and written documents

No Comments

No Known Activations