INDEX

Explanations

words related to computer programming and technology

oai_token-act-pair · gpt-3.5-turbo

references to specific items or brands, particularly in relation to products or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Britann

-0.74

crim

-0.72

wright

-0.71

 Warner

-0.71

 Albion

-0.68

castle

-0.68

 Gand

-0.67

hesda

-0.65

hire

-0.64

theless

-0.63

POSITIVE LOGITS

ixture

1.05

umps

1.03

enses

1.02

umper

0.94

ockets

0.94

uctions

0.93

apping

0.93

otation

0.93

agging

0.92

airs

0.91

Activations Density 0.166%

words related to computer programming and technology

references to specific items or brands, particularly in relation to products or events

No Comments

No Known Activations