INDEX

Explanations

specific positions or locations within objects or structures

oai_token-act-pair · gpt-3.5-turbo

phrases related to technical specifications and details of products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Reporting

-0.61

udden

-0.61

Polit

-0.60

 Economist

-0.59

 UNCLASSIFIED

-0.57

laim

-0.57

 tacit

-0.57

ansom

-0.56

 perpetrated

-0.55

urdue

-0.55

POSITIVE LOGITS

 each

1.02

neath

0.94

the

0.88

clusions

0.84

 this

0.83

 these

0.80

 turrets

0.79

tones

0.79

 mine

0.73

 textures

0.73

Activations Density 0.402%

specific positions or locations within objects or structures

phrases related to technical specifications and details of products

No Comments

No Known Activations